Happy holidays! We’ll be sharing snippets from Latent Space LIVE! through the break bringing you the best of 2024! We want to express our deepest appreciation to event sponsors AWS, Daylight Computer, Thoth.ai, StrongCompute, Notable Capital, and most of all all our LS supporters who helped fund the gorgeous venue and A/V production!For NeurIPS last year we did our standard conference podcast coverage interviewing selected papers (that we have now also done for ICLR and ICML), however we felt that we could be doing more to help AI Engineers 1) get more industry-relevant content, and 2) recap 2024 year in review from experts. As a result, we organized the first Latent Space LIVE!, our first in person miniconference, at NeurIPS 2024 in Vancouver.Our next keynote covers The State of LLM Agents, with the triumphant return of Professor Graham Neubig’s return to the pod (his ICLR episode here!). OpenDevin is now a startup known as AllHands! The renamed OpenHands has done extremely well this year, as they end the year sitting comfortably at number 1 on the hardest SWE-Bench Full leaderboard at 29%, though on the smaller SWE-Bench Verified, they are at 53%, behind Amazon Q, devlo, and OpenAI's self reported o3 results at 71.7%.Many are saying that 2025 is going to be the year of agents, with OpenAI, DeepMind and Anthropic setting their sights on consumer and coding agents, vision based computer-using agents and multi agent systems. There has been so much progress on the practical reliability and applications of agents in all domains, from the huge launch of Cognition AI's Devin this year, to the sleeper hit of Cursor Composer and Codeium's Windsurf Cascade in the IDE arena, to the explosive revenue growth of Stackblitz's Bolt, Lovable, and Vercel's v0, and the unicorn rounds and high profile movements of customer support agents like Sierra (now worth $4 billion) and search agents like Perplexity (now worth $9 billion). We wanted to take a little step back to understand the most notable papers of the year in Agents, and Graham indulged with his list of 8 perennial problems in building agents in 2024.Must-Read Papers for the 8 Problems of Agents* The agent-computer interface: CodeAct: Executable Code Actions Elicit Better LLM Agents. Minimial viable tools: Execution Sandbox, File Editor, Web Browsing* The human-agent interface: Chat UI, GitHub Plugin, Remote runtime, …?* Choosing an LLM: See Evaluation of LLMs as Coding Agents on SWE-Bench at 30x - must understand instructions, tools, code, environment, error recovery* Planning: Single Agent Systems vs Multi Agent (CoAct: A Global-Local Hierarchy for Autonomous Agent Collaboration) - Explicit vs Implicit, Curated vs Generated* Reusable common workflows: SteP: Stacked LLM Policies for Web Actions and Agent Workflow Memory - Manual prompting vs Learning from Experience* Exploration: Agentless: Demystifying LLM-based Software Engineering Agents and BAGEL: Bootstrapping Agents by Guiding Exploration with Language* Search: Tree Search for Language Model Agents - explore paths and rewind* Evaluation: Fast Sanity Checks (miniWoB and Aider) and Highly Realistic (WebArena, SWE-Bench) and SWE-Gym: An Open Environment for Training Software Engineering Agents & VerifiersFull Talk on YouTubePlease like and subscribe!Timestamps* 00:00 Welcome to Latent Space Live at NeurIPS 2024* 00:29 State of LLM Agents in 2024* 02:20 Professor Graham Newbig's Insights on Agents* 03:57 Live Demo: Coding Agents in Action* 08:20 Designing Effective Agents* 14:13 Choosing the Right Language Model for Agents* 16:24 Planning and Workflow for Agents* 22:21 Evaluation and Future Predictions for Agents* 25:31 Future of Agent Development* 25:56 Human-Agent Interaction Challenges* 26:48 Expanding Agent Use Beyond Programming* 27:25 Redesigning Systems for Agent Efficiency* 28:03 Accelerating Progress with Agent Technology* 28:28 Call to Action for Open Source Contributions* 30:36 Q&A: Agent Performance and Benchmarks* 33:23 Q&A: Web Agents and Interaction Methods* 37:16 Q&A: Agent Architectures and Improvements* 43:09 Q&A: Self-Improving Agents and Authentication* 47:31 Live Demonstration and Closing RemarksTranscript[00:00:29] State of LLM Agents in 2024[00:00:29] Speaker 9: Our next keynote covers the state of LLM agents. With the triumphant return of Professor Graham Newbig of CMU and OpenDevon, now a startup known as AllHands. The renamed OpenHands has done extremely well this year, as they end the year sitting comfortably at number one on the hardest SWE Benchful leaderboard at 29%.[00:00:53] Speaker 9: Though, on the smaller SWE bench verified, they are at 53 percent behind Amazon Q [00:01:00] Devlo and OpenAI's self reported O3 results at 71. 7%. Many are saying that 2025 is going to be the year of agents, with OpenAI, DeepMind, and Anthropic setting their sights on consumer and coding agents. Vision based computer using agents and multi agent systems.[00:01:22] Speaker 9: There has been so much progress on the practical reliability and applications of agents in all domains, from the huge launch of Cognition AI's Devon this year, to the sleeper hit of Cursor Composer and recent guest Codium's Windsurf Cascade in the IDE arena. To the explosive revenue growth of recent guests StackBlitz's Bolt, Lovable, and Vercel's vZero.[00:01:44] Speaker 9: And the unicorn rounds and high profile movements of customer support agents like Sierra, now worth 4 billion, and search agents like Perplexity, now worth 9 billion. We wanted to take a little step back to understand the most notable papers of the year in [00:02:00] agents, and Graham indulged with his list of eight perennial problems in building agents.[00:02:06] Speaker 9: As always, don't forget to check our show notes for all the selected best papers of 2024, and for the YouTube link to their talk. Graham's slides were especially popular online, and we are honoured to have him. Watch out and take care![00:02:20] Professor Graham Newbig's Insights on Agents[00:02:20] Speaker: Okay hi everyone. So I was given the task of talking about agents in 2024, and this is An impossible task because there are so many agents, so many agents in 2024. So this is going to be strongly covered by like my personal experience and what I think is interesting and important, but I think it's an important topic.[00:02:41] Speaker: So let's go ahead. So the first thing I'd like to think about is let's say I gave you you know, a highly competent human, some tools. Let's say I gave you a web browser and a terminal or a file system. And the ability to [00:03:00] edit text or code. What could you do with that? Everything. Yeah.[00:03:07] Speaker: Probably a lot of things. This is like 99 percent of my, you know, daily daily life, I guess. When I'm, when I'm working. So, I think this is a pretty powerful tool set, and I am trying to do, and what I think some other people are trying to do, is come up with agents that are able to, you know, manipulate these things.[00:03:26] Speaker: Web browsing, coding, running code in successful ways. So there was a little bit about my profile. I'm a professor at CMU, chief scientist at All Hands AI, building open source coding agents. I'm maintainer of OpenHands, which is an open source coding agent framework. And I'm also a software developer and I, I like doing lots of coding and, and, you know, shipping new features and stuff like this.[00:03:51] Speaker: So building agents that help me to do this, you know, is kind of an interesting thing, very close to me.[00:03:57] Live Demo: Coding Agents in Action[00:03:57] Speaker: So the first thing I'd like to do is I'd like to try [00:04:00] some things that I haven't actually tried before. If anybody has, you know, tried to give a live demo, you know, this is, you know very, very scary whenever you do it and it might not work.[00:04:09] Speaker: So it might not work this time either. But I want to show you like three things that I typically do with coding agents in my everyday work. I use coding agents maybe five to 10 times a day to help me solve my own problems. And so this is a first one. This is a data science task. Which says I want to create scatter plots that show the increase of the SWE bench score over time.[00:04:34] Speaker: And so I, I wrote a kind of concrete prompt about this. Agents work better with like somewhat concrete prompts. And I'm gonna throw this into open hands and let it work. And I'll, I'll go back to that in a second. Another thing that I do is I create new software. And I, I've been using a [00:05:00] service a particular service.[00:05:01] Speaker: I won't name it for sending emails and I'm not very happy with it. So I want to switch over to this new service called resend. com, which makes it easier to send emails. And so I'm going to ask it to read the docs for the resend. com API and come up with a script that allows me to send emails. The input to the script should be a CSV file and the subject and body should be provided in Jinja2 templates.[00:05:24] Speaker: So I'll start another agent and and try to get it to do that for me.[00:05:35] Speaker: And let's go with the last one. The last one I do is. This is improving existing software and in order, you know, once you write software, you usually don't throw it away. You go in and, like, actually improve it iteratively. This software that I have is something I created without writing any code.[00:05:52] Speaker: It's basically software to monitor how much our our agents are contributing to the OpenHance repository. [00:06:00] And on the, let me make that a little bit bigger, on the left side, I have the number of issues where it like sent a pull request. I have the number of issues where it like sent a pull request, whether it was merged in purple, closed in red, or is still open in green. And so these are like, you know, it's helping us monitor, but one thing it doesn't tell me is the total number. And I kind of want that
Happy holidays! We’ll be sharing snippets from Latent Space LIVE! through the break bringing you the best of 2024! We want to express our deepest appreciation to event sponsors AWS, Daylight Computer, Thoth.ai, StrongCompute, Notable Capital, and most of all all our LS supporters who helped fund the gorgeous venue and A/V production!For NeurIPS last year we did our standard conference podcast coverage interviewing selected papers (that we have now also done for ICLR and ICML), however we felt that we could be doing more to help AI Engineers 1) get more industry-relevant content, and 2) recap 2024 year in review from experts. As a result, we organized the first Latent Space LIVE!, our first in person miniconference, at NeurIPS 2024 in Vancouver. Today, we’re proud to share Loubna’s highly anticipated talk (slides here)!Synthetic DataWe called out the Synthetic Data debate at last year’s NeurIPS, and no surprise that 2024 was dominated by the rise of synthetic data everywhere:* Apple’s Rephrasing the Web, Microsoft’s Phi 2-4 and Orca/AgentInstruct, Tencent’s Billion Persona dataset, DCLM, and HuggingFace’s FineWeb-Edu, and Loubna’s own Cosmopedia extended the ideas of synthetic textbook and agent generation to improve raw web scrape dataset quality* This year we also talked to the IDEFICS/OBELICS team at HuggingFace who released WebSight this year, the first work on code-vs-images synthetic data.* We called Llama 3.1 the Synthetic Data Model for its extensive use (and documentation!) of synthetic data in its pipeline, as well as its permissive license. * Nemotron CC and Nemotron-4-340B also made a big splash this year for how they used 20k items of human data to synthesize over 98% of the data used for SFT/PFT.* Cohere introduced Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress observing gains of up to 56.5% improvement in win rates comparing multiple teachers vs the single best teacher model* In post training, AI2’s Tülu3 (discussed by Luca in our Open Models talk) and Loubna’s Smol Talk were also notable open releases this year.This comes in the face of a lot of scrutiny and criticism, with Scale AI as one of the leading voices publishing AI models collapse when trained on recursively generated data in Nature magazine bringing mainstream concerns to the potential downsides of poor quality syndata:Part of the concerns we highlighted last year on low-background tokens are coming to bear: ChatGPT contaminated data is spiking in every possible metric:But perhaps, if Sakana’s AI Scientist pans out this year, we will have mostly-AI AI researchers publishing AI research anyway so do we really care as long as the ideas can be verified to be correct?Smol ModelsMeta surprised many folks this year by not just aggressively updating Llama 3 and adding multimodality, but also adding a new series of “small” 1B and 3B “on device” models this year, even working on quantized numerics collaborations with Qualcomm, Mediatek, and Arm. It is near unbelievable that a 1B model today can qualitatively match a 13B model of last year:and the minimum size to hit a given MMLU bar has come down roughly 10x in the last year. We have been tracking this proxied by Lmsys Elo and inference price:The key reads this year are:* MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases* Apple Intelligence Foundation Language Models* Hymba: A Hybrid-head Architecture for Small Language Models* Loubna’s SmolLM and SmolLM2: a family of state-of-the-art small models with 135M, 360M, and 1.7B parameters on the pareto efficiency frontier.* and Moondream, which we already covered in the 2024 in Vision talkFull Talk on YouTubeplease like and subscribe!Timestamps* [00:00:05] Loubna Intro* [00:00:33] The Rise of Synthetic Data Everywhere* [00:02:57] Model Collapse* [00:05:14] Phi, FineWeb, Cosmopedia - Synthetic Textbooks* [00:12:36] DCLM, Nemotron-CC* [00:13:28] Post Training - AI2 Tulu, Smol Talk, Cohere Multilingual Arbitrage* [00:16:17] Smol Models* [00:18:24] On Device Models* [00:22:45] Smol Vision Models* [00:25:14] What's NextTranscript2024 in Synthetic Data and Smol Models[00:00:00] [00:00:05] Loubna Intro[00:00:05] Speaker: I'm very happy to be here. Thank you for the invitation. So I'm going to be talking about synthetic data in 2024. And then I'm going to be talking about small on device models. So I think the most interesting thing about synthetic data this year is that like now we have it everywhere in the large language models pipeline.[00:00:33] The Rise of Synthetic Data Everywhere[00:00:33] Speaker: I think initially, synthetic data was mainly used just for post training, because naturally that's the part where we needed human annotators. And then after that, we realized that we don't really have good benchmarks to [00:01:00] measure if models follow instructions well, if they are creative enough, or if they are chatty enough, so we also started using LLMs as judges.[00:01:08] Speaker: Thank you. And I think this year and towards the end of last year, we also went to the pre training parts and we started generating synthetic data for pre training to kind of replace some parts of the web. And the motivation behind that is that you have a lot of control over synthetic data. You can control your prompt and basically also the kind of data that you generate.[00:01:28] Speaker: So instead of just trying to filter the web, you could try to get the LLM to generate what you think the best web pages could look like and then train your models on that. So this is how we went from not having synthetic data at all in the LLM pipeline to having it everywhere. And so the cool thing is like today you can train an LLM with like an entirely synthetic pipeline.[00:01:49] Speaker: For example, you can use our Cosmopedia datasets and you can train a 1B model on like 150 billion tokens that are 100 percent synthetic. And those are also of good quality. And then you can [00:02:00] instruction tune the model on a synthetic SFT dataset. You can also do DPO on a synthetic dataset. And then to evaluate if the model is good, you can use.[00:02:07] Speaker: A benchmark that uses LLMs as a judge, for example, MTBench or AlpacaEvil. So I think this is like a really mind blowing because like just a few years ago, we wouldn't think this is possible. And I think there's a lot of concerns about model collapse, and I'm going to talk about that later. But we'll see that like, if we use synthetic data properly and we curate it carefully, that shouldn't happen.[00:02:29] Speaker: And the reason synthetic data is very popular right now is that we have really strong models, both open and closed. It is really cheap and fast to use compared to human annotations, which cost a lot and take a lot of time. And also for open models right now, we have some really good inference frameworks.[00:02:47] Speaker: So if you have enough GPUs, it's really easy to spawn these GPUs and generate like a lot of synthetic data. Some examples are VLM, TGI, and TensorRT.[00:02:57] Model Collapse[00:02:57] Speaker: Now let's talk about the elephant in the room, model [00:03:00] collapse. Is this the end? If you look at the media and all of like, for example, some papers in nature, it's really scary because there's a lot of synthetic data out there in the web.[00:03:09] Speaker: And naturally we train on the web. So we're going to be training a lot of synthetic data. And if model collapse is going to happen, we should really try to take that seriously. And the other issue is that, as I said, we think, a lot of people think the web is polluted because there's a lot of synthetic data.[00:03:24] Speaker: And for example, when we're building fine web datasets here at Guillerm and Hinek, we're interested in like, how much synthetic data is there in the web? So there isn't really a method to properly measure the amount of synthetic data or to save a webpage synthetic or not. But one thing we can do is to try to look for like proxy words, for example, expressions like as a large language model or words like delve that we know are actually generated by chat GPT.[00:03:49] Speaker: We could try to measure the amount of these words in our data system and compare them to the previous years. For example, here, we measured like a, these words ratio in different dumps of common crawl. [00:04:00] And we can see that like the ratio really increased after chat GPT's release. So if we were to say that synthetic data amount didn't change, you would expect this ratio to stay constant, which is not the case.[00:04:11] Speaker: So there's a lot of synthetic data probably on the web, but does this really make models worse? So what we did is we trained different models on these different dumps. And we then computed their performance on popular, like, NLP benchmarks, and then we computed the aggregated score. And surprisingly, you can see that the latest DOMs are actually even better than the DOMs that are before.[00:04:31] Speaker: So if there's some synthetic data there, at least it did not make the model's worse. Yeah, which is really encouraging. So personally, I wouldn't say the web is positive with Synthetic Data. Maybe it's even making it more rich. And the issue with like model collapse is that, for example, those studies, they were done at like a small scale, and you would ask the model to complete, for example, a Wikipedia paragraph, and then you would train it on these new generations, and you would do that every day.[00:04:56] Speaker: iteratively. I think if you do that approach, it's normal to [00:05:00] observe this kind of behavior because the quality is going to be worse because the model is already small. And then if you train it just on its generations, you shouldn't expect it to become better. But what we're really doing here is that we take a model that is very large and we try to distill its knowledge into a model that is smaller.[00:05:14] Phi, Fin
Happy holidays! We’ll be sharing snippets from Latent Space LIVE! through the break bringing you the best of 2024! We want to express our deepest appreciation to event sponsors AWS, Daylight Computer, Thoth.ai, StrongCompute, Notable Capital, and most of all all our LS supporters who helped fund the gorgeous venue and A/V production!For NeurIPS last year we did our standard conference podcast coverage interviewing selected papers (that we have now also done for ICLR and ICML), however we felt that we could be doing more to help AI Engineers 1) get more industry-relevant content, and 2) recap 2024 year in review from experts. As a result, we organized the first Latent Space LIVE!, our first in person miniconference, at NeurIPS 2024 in Vancouver.Of perennial interest, particularly at academic conferences, is scaled-up architecture research as people hunt for the next Attention Is All You Need. We have many names for them: “efficient models”, “retentive networks”, “subquadratic attention” or “linear attention” but some of them don’t even have any lineage with attention - one of the best papers of this NeurIPS was Sepp Hochreiter’s xLSTM, which has a particularly poetic significance as one of the creators of the LSTM returning to update and challenge the OG language model architecture:So, for lack of a better term, we decided to call this segment “the State of Post-Transformers” and fortunately everyone rolled with it.We are fortunate to have two powerful friends of the pod to give us an update here:* Together AI: with CEO Vipul Ved Prakash and CTO Ce Zhang joining us to talk about how they are building Together together as a quote unquote full stack AI startup, from the lowest level kernel and systems programming to the highest level mathematical abstractions driving new model architectures and inference algorithms, with notable industry contributions from RedPajama v2, Flash Attention 3, Mamba 2, Mixture of Agents, BASED, Sequoia, Evo, Dragonfly, Dan Fu's ThunderKittens and many more research projects this year* Recursal AI: with CEO Eugene Cheah who has helped lead the independent RWKV project while also running Featherless AI. This year, the team has shipped RWKV v5, codenamed Eagle, to 1.5 billion Windows 10 and Windows 11 machines worldwide, to support Microsoft's on-device, energy-usage-sensitive Windows Copilot usecases, and has launched the first updates on RWKV v6, codenamed Finch and GoldFinch. On the morning of Latent Space Live, they also announced QRWKV6, a Qwen 32B model modified with RWKV linear attention layers. We were looking to host a debate between our speakers, but given that both of them were working on post-transformers alternativesFull Talk on YoutubePlease like and subscribe!LinksAll the models and papers they picked:* Earlier Cited Work* Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention* Hungry hungry hippos: Towards language modeling with state space models* Hyena hierarchy: Towards larger convolutional language models* Mamba: Linear-Time Sequence Modeling with Selective State Spaces* S4: Efficiently Modeling Long Sequences with Structured State Spaces* Just Read Twice (Arora et al)* Recurrent large language models that compete with Transformers in language modeling perplexity are emerging at a rapid rate (e.g., Mamba, RWKV). Excitingly, these architectures use a constant amount of memory during inference. However, due to the limited memory, recurrent LMs cannot recall and use all the information in long contexts leading to brittle in-context learning (ICL) quality. A key challenge for efficient LMs is selecting what information to store versus discard. In this work, we observe the order in which information is shown to the LM impacts the selection difficulty. * To formalize this, we show that the hardness of information recall reduces to the hardness of a problem called set disjointness (SD), a quintessential problem in communication complexity that requires a streaming algorithm (e.g., recurrent model) to decide whether inputted sets are disjoint. We empirically and theoretically show that the recurrent memory required to solve SD changes with set order, i.e., whether the smaller set appears first in-context. * Our analysis suggests, to mitigate the reliance on data order, we can put information in the right order in-context or process prompts non-causally. Towards that end, we propose: (1) JRT-Prompt, where context gets repeated multiple times in the prompt, effectively showing the model all data orders. This gives 11.0±1.3 points of improvement, averaged across 16 recurrent LMs and the 6 ICL tasks, with 11.9× higher throughput than FlashAttention-2 for generation prefill (length 32k, batch size 16, NVidia H100). We then propose (2) JRT-RNN, which uses non-causal prefix-linear-attention to process prompts and provides 99% of Transformer quality at 360M params., 30B tokens and 96% at 1.3B params., 50B tokens on average across the tasks, with 19.2× higher throughput for prefill than FA2.* Jamba: A 52B Hybrid Transformer-Mamba Language Model* We present Jamba, a new base large language model based on a novel hybrid Transformer-Mamba mixture-of-experts (MoE) architecture. * Specifically, Jamba interleaves blocks of Transformer and Mamba layers, enjoying the benefits of both model families. MoE is added in some of these layers to increase model capacity while keeping active parameter usage manageable. * This flexible architecture allows resource- and objective-specific configurations. In the particular configuration we have implemented, we end up with a powerful model that fits in a single 80GB GPU.* Built at large scale, Jamba provides high throughput and small memory footprint compared to vanilla Transformers, and at the same time state-of-the-art performance on standard language model benchmarks and long-context evaluations. Remarkably, the model presents strong results for up to 256K tokens context length. * We study various architectural decisions, such as how to combine Transformer and Mamba layers, and how to mix experts, and show that some of them are crucial in large scale modeling. We also describe several interesting properties of these architectures which the training and evaluation of Jamba have revealed, and plan to release checkpoints from various ablation runs, to encourage further exploration of this novel architecture. We make the weights of our implementation of Jamba publicly available under a permissive license.* SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers* We introduce Sana, a text-to-image framework that can efficiently generate images up to 4096×4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU. Core designs include: * (1) Deep compression autoencoder: unlike traditional AEs, which compress images only 8×, we trained an AE that can compress images 32×, effectively reducing the number of latent tokens. * (2) Linear DiT: we replace all vanilla attention in DiT with linear attention, which is more efficient at high resolutions without sacrificing quality. * (3) Decoder-only text encoder: we replaced T5 with modern decoder-only small LLM as the text encoder and designed complex human instruction with in-context learning to enhance the image-text alignment. * (4) Efficient training and sampling: we propose Flow-DPM-Solver to reduce sampling steps, with efficient caption labeling and selection to accelerate convergence. * As a result, Sana-0.6B is very competitive with modern giant diffusion model (e.g. Flux-12B), being 20 times smaller and 100+ times faster in measured throughput. Moreover, Sana-0.6B can be deployed on a 16GB laptop GPU, taking less than 1 second to generate a 1024×1024 resolution image. Sana enables content creation at low cost. * RWKV: Reinventing RNNs for the Transformer Era* Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence length. In contrast, recurrent neural networks (RNNs) exhibit linear scaling in memory and computational requirements but struggle to match the same performance as Transformers due to limitations in parallelization and scalability. * We propose a novel model architecture, Receptance Weighted Key Value (RWKV), that combines the efficient parallelizable training of transformers with the efficient inference of RNNs.* Our approach leverages a linear attention mechanism and allows us to formulate the model as either a Transformer or an RNN, thus parallelizing computations during training and maintains constant computational and memory complexity during inference. * We scale our models as large as 14 billion parameters, by far the largest dense RNN ever trained, and find RWKV performs on par with similarly sized Transformers, suggesting future work can leverage this architecture to create more efficient models. This work presents a significant step towards reconciling trade-offs between computational efficiency and model performance in sequence processing tasks.* LoLCATs: On Low-Rank Linearizing of Large Language Models* Recent works show we can linearize large language models (LLMs) -- swapping the quadratic attentions of popular Transformer-based LLMs with subquadratic analogs, such as linear attention -- avoiding the expensive pretraining costs. However, linearizing LLMs often significantly degrades model quality, still requires training over billions of tokens, and remains limited to smaller 1.3B to 7B LLMs. * We thus propose Low-rank Linear Conversion via Attention Transfer (LoLCATs), a simple two-step method that improves LLM linearizing quality with orders of magnitudes less memory and compute. * We base these steps on two findings. * First, we can replace an LLM's softmax attentions with closely-approximating linear attentions,
Happy holidays! We’ll be sharing snippets from Latent Space LIVE! through the break bringing you the best of 2024! We want to express our deepest appreciation to event sponsors AWS, Daylight Computer, Thoth.ai, StrongCompute, Notable Capital, and most of all our LS supporters who helped fund the venue and A/V production!For NeurIPS last year we did our standard conference podcast coverage interviewing selected papers (that we have now also done for ICLR and ICML), however we felt that we could be doing more to help AI Engineers 1) get more industry-relevant content, and 2) recap 2024 year in review from experts. As a result, we organized the first Latent Space LIVE!, our first in person miniconference, at NeurIPS 2024 in Vancouver.Since Nathan Lambert ( Interconnects ) joined us for the hit RLHF 201 episode at the start of this year, it is hard to overstate how much Open Models have exploded this past year. In 2023 only five names were playing in the top LLM ranks, Mistral, Mosaic's MPT, TII UAE's Falcon, Yi from Kai-Fu Lee's 01.ai, and of course Meta's Llama 1 and 2. This year a whole cast of new open models have burst on the scene, from Google's Gemma and Cohere's Command R, to Alibaba's Qwen and Deepseek models, to LLM 360 and DCLM and of course to the Allen Institute's OLMo, OL MOE, Pixmo, Molmo, and Olmo 2 models. We were honored to host Luca Soldaini, one of the research leads on the Olmo series of models at AI2.Pursuing Open Model research comes with a lot of challenges beyond just funding and access to GPUs and datasets, particularly the regulatory debates this year across Europe, California and the White House. We also were honored to hear from and Sophia Yang, head of devrel at Mistral, who also presented a great session at the AI Engineer World's Fair Open Models track!Full Talk on YouTubePlease like and subscribe!Timestamps* 00:00 Welcome to Latent Space Live * 00:12 Recap of 2024: Best Moments and Keynotes * 01:22 Explosive Growth of Open Models in 2024 * 02:04 Challenges in Open Model Research * 02:38 Keynote by Luca Soldani: State of Open Models * 07:23 Significance of Open Source AI Licenses * 11:31 Research Constraints and Compute Challenges * 13:46 Fully Open Models: A New Trend * 27:46 Mistral's Journey and Innovations * 32:57 Interactive Demo: Lachat Capabilities * 36:50 Closing Remarks and NetworkingTranscriptSession3Audio[00:00:00] AI Charlie: Welcome to Latent Space Live, our first mini conference held at NeurIPS 2024 in Vancouver. This is Charlie, your AI co host. As a special treat this week, we're recapping the best of 2024 going domain by domain. We sent out a survey to the over 900 of you who told us what you wanted, and then invited the best speakers in the latent space network to cover each field.[00:00:28] AI Charlie: 200 of you joined us in person throughout the day, with over 2, 200 watching live online. Our next keynote covers the state of open models in 2024, with Luca Soldani and Nathan Lambert of the Allen Institute for AI, with a special appearance from Dr. Sophia Yang of Mistral. Our first hit episode of 2024 was with Nathan Lambert on RLHF 201 back in January.[00:00:57] AI Charlie: Where he discussed both reinforcement learning for language [00:01:00] models and the growing post training and mid training stack with hot takes on everything from constitutional AI to DPO to rejection sampling and also previewed the sea change coming to the Allen Institute. And to Interconnects, his incredible substack on the technical aspects of state of the art AI training.[00:01:18] AI Charlie: We highly recommend subscribing to get access to his Discord as well. It is hard to overstate how much open models have exploded this past year. In 2023, only five names were playing in the top LLM ranks. Mistral, Mosaics MPT, and Gatsby. TII UAE's Falcon, Yi, from Kaifu Lee's 01. ai, And of course, Meta's Lama 1 and 2.[00:01:43] AI Charlie: This year, a whole cast of new open models have burst on the scene. From Google's Jemma and Cohere's Command R, To Alibaba's Quen and DeepSeq models, to LLM360 and DCLM, and of course, to the Allen Institute's OLMO, [00:02:00] OLMOE, PIXMO, MOLMO, and OLMO2 models. Pursuing open model research comes with a lot of challenges beyond just funding and access to GPUs and datasets, particularly the regulatory debates this year across Europe.[00:02:14] AI Charlie: California and the White House. We also were honored to hear from Mistral, who also presented a great session at the AI Engineer World's Fair Open Models track. As always, don't forget to check the show notes for the YouTube link to their talk, as well as their slides. Watch out and take care.[00:02:35] Luca Intro[00:02:35] Luca Soldaini: Cool. Yeah, thanks for having me over. I'm Luca. I'm a research scientist at the Allen Institute for AI. I threw together a few slides on sort of like a recap of like interesting themes in open models for, for 2024. Have about maybe 20, 25 minutes of slides, and then we can chat if there are any questions.[00:02:57] Luca Soldaini: If I can advance to the next slide. [00:03:00] Okay, cool. So I did the quick check of like, to sort of get a sense of like, how much 2024 was different from 2023. So I went on Hugging Face and sort of get, tried to get a picture of what kind of models were released in 2023 and like, what do we get in 2024?[00:03:16] Luca Soldaini: 2023 we get, we got things like both LLAMA 1 and 2, we got Mistral, we got MPT, Falcon models, I think the YI model came in at the end. Tail end of the year. It was a pretty good year. But then I did the same for 2024. And it's actually quite stark difference. You have models that are, you know, reveling frontier level.[00:03:38] Luca Soldaini: Performance of what you can get from closed models from like Quen, from DeepSeq. We got Llama3. We got all sorts of different models. I added our own Olmo at the bottom. There's this growing group of like, Fully open models that I'm going to touch on a little bit later. But you know, just looking at the slides, it feels like 2024 [00:04:00] was just smooth sailing, happy knees, much better than previous year.[00:04:04] Luca Soldaini: And you know, you can plot you can pick your favorite benchmark Or least favorite, I don't know, depending on what point you're trying to make. And plot, you know, your closed model, your open model and sort of spin it in ways that show that, oh, you know open models are much closer to where closed models are today versus to Versus last year where the gap was fairly significant.[00:04:29] Luca Soldaini: So one thing that I think I don't know if I have to convince people in this room, but usually when I give this talks about like open models, there is always like this background question in, in, in people's mind of like, why should we use open models? APIs argument, you know, it's, it's. Just an HTTP request to get output from a, from one of the best model out there.[00:04:53] Luca Soldaini: Why do I have to set up infra and use local models? And there are really like two answer. There is the more [00:05:00] researchy answer for this, which is where it might be. Background lays, which is just research. If you want to do research on language models, research thrives on, on open models, there is like large swath of research on modeling, on how these models behave on evaluation and inference on mechanistic interpretability that could not happen at all if you didn't have open models they're also for AI builders, they're also like.[00:05:30] Luca Soldaini: Good use cases for using local models. You know, you have some, this is like a very not comprehensive slides, but you have things like there are some application where local models just blow closed models out of the water. So like retrieval, it's a very clear example. We might have like constraints like Edge AI applications where it makes sense.[00:05:51] Luca Soldaini: But even just like in terms of like stability, being able to say this model is not changing under the hood. It's, there's plenty of good cases for, [00:06:00] for open models. And the community is just not models. Is I stole this slide from one of the Quent2 announcement blog posts. But it's super cool to see like how much tech exists around open models and serving them on making them efficient and hosting them.[00:06:18] Luca Soldaini: It's pretty cool. And so. It's if you think about like where the term opens come from, comes from like the open source really open models meet the core tenants of, of open, of open source specifically when it comes around collaboration, there is truly a spirit, like through these open models, you can build on top of other people.[00:06:41] Luca Soldaini: innovation. We see a lot of these even in our own work of like, you know, as we iterate in the various versions of Alma it's not just like every time we collect from scratch all the data. No, the first step is like, okay, what are the cool data sources and datasets people have put [00:07:00] together for language model for training?[00:07:01] Luca Soldaini: Or when it comes to like our post training pipeline We one of the steps is you want to do some DPO and you use a lot of outputs of other models to improve your, your preference model. So it's really having like an open sort of ecosystem benefits and accelerates the development of open models.[00:07:23] The Definition of Open Models[00:07:23] Luca Soldaini: One thing that we got in 2024, which is not a specific model, but I thought it was really significant, is we first got we got our first open source AI definition. So this is from the open source initiative they've been generally the steward of a lot of the open source licenses when it comes to software and so they embarked on this journey in trying to figure out, okay, How does a license, an open source license for a model look like?[00:07:52] Luca Soldaini: Majority of the work is very dry because licenses are dry. So I'm not going to walk through t
Happy holidays! We’ll be sharing snippets from Latent Space LIVE! through the break bringing you the best of 2024! We want to express our deepest appreciation to event sponsors AWS, Daylight Computer, Thoth.ai, StrongCompute, Notable Capital, and most of all all our LS supporters who helped fund the gorgeous venue and A/V production!For NeurIPS last year we did our standard conference podcast coverage interviewing selected papers (that we have now also done for ICLR and ICML), however we felt that we could be doing more to help AI Engineers 1) get more industry-relevant content, and 2) recap 2024 year in review from experts. As a result, we organized the first Latent Space LIVE!, our first in person miniconference, at NeurIPS 2024 in Vancouver.The single most requested domain was computer vision, and we could think of no one better to help us recap 2024 than our friends at Roboflow, who was one of our earliest guests in 2023 and had one of this year’s top episodes in 2024 again. Roboflow has since raised a $40m Series B!LinksAll the trends and papers they picked:* Isaac Robinson* Sora (see our Video Diffusion pod) - extending diffusion from images to video* SAM 2: Segment Anything in Images and Videos (see our SAM2 pod) - extending prompted masks to full video object segmentation* DETR Dominancy: DETRs show Pareto improvement over YOLOs* RT-DETR: DETRs Beat YOLOs on Real-time Object Detection* LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection* D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement* Peter Robicheaux* MMVP (Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs)* * Florence 2 (Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks) * PalíGemma / PaliGemma 2* PaliGemma: A versatile 3B VLM for transfer* PaliGemma 2: A Family of Versatile VLMs for Transfer* AlMv2 (Multimodal Autoregressive Pre-training of Large Vision Encoders) * Vik Korrapati - MoondreamFull Talk on YouTubeWant more content like this? Like and subscribe to stay updated on our latest talks, interviews, and podcasts.Transcript/Timestamps[00:00:00] Intro[00:00:05] AI Charlie: welcome to Latent Space Live, our first mini conference held at NeurIPS 2024 in Vancouver. This is Charlie, your AI co host. When we were thinking of ways to add value to our academic conference coverage, we realized that there was a lack of good talks, just recapping the best of 2024, going domain by domain.[00:00:36] AI Charlie: We sent out a survey to the over 900 of you. who told us what you wanted, and then invited the best speakers in the Latent Space Network to cover each field. 200 of you joined us in person throughout the day, with over 2, 200 watching live online. Our second featured keynote is The Best of Vision 2024, with Peter Robichaud and Isaac [00:01:00] Robinson of Roboflow, with a special appearance from Vic Corrapati of Moondream.[00:01:05] AI Charlie: When we did a poll of our attendees, the highest interest domain of the year was vision. And so our first port of call was our friends at Roboflow. Joseph Nelson helped us kickstart our vision coverage in episode 7 last year, and this year came back as a guest host with Nikki Ravey of Meta to cover segment Anything 2.[00:01:25] AI Charlie: Roboflow have consistently been the leaders in open source vision models and tooling. With their SuperVision library recently eclipsing PyTorch's Vision library. And Roboflow Universe hosting hundreds of thousands of open source vision datasets and models. They have since announced a 40 million Series B led by Google Ventures.[00:01:46] AI Charlie: Woohoo.[00:01:48] Isaac's picks[00:01:48] Isaac Robinson: Hi, we're Isaac and Peter from Roboflow, and we're going to talk about the best papers of 2024 in computer vision. So, for us, we defined best as what made [00:02:00] the biggest shifts in the space. And to determine that, we looked at what are some major trends that happened and what papers most contributed to those trends.[00:02:09] Isaac Robinson: So I'm going to talk about a couple trends, Peter's going to talk about a trend, And then we're going to hand it off to Moondream. So, the trends that I'm interested in talking about are These are a major transition from models that run on per image basis to models that run using the same basic ideas on video.[00:02:28] Isaac Robinson: And then also how debtors are starting to take over the real time object detection scene from the YOLOs, which have been dominant for years.[00:02:37] Sora, OpenSora and Video Vision vs Generation[00:02:37] Isaac Robinson: So as a highlight we're going to talk about Sora, which from my perspective is the biggest paper of 2024, even though it came out in February. Is the what?[00:02:48] Isaac Robinson: Yeah. Yeah. So just it's a, SORA is just a a post. So I'm going to fill it in with details from replication efforts, including open SORA and related work, such as a stable [00:03:00] diffusion video. And then we're also going to talk about SAM2, which applies the SAM strategy to video. And then how debtors, These are the improvements in 2024 to debtors that are making them a Pareto improvement to YOLO based models.[00:03:15] Isaac Robinson: So to start this off, we're going to talk about the state of the art of video generation at the end of 2023, MagVIT MagVIT is a discrete token, video tokenizer akin to VQ, GAN, but applied to video sequences. And it actually outperforms state of the art handcrafted video compression frameworks.[00:03:38] Isaac Robinson: In terms of the bit rate versus human preference for quality and videos generated by autoregressing on these discrete tokens generate some pretty nice stuff, but up to like five seconds length and, you know, not super detailed. And then suddenly a few months later we have this, which when I saw it, it was totally mind blowing to me.[00:03:59] Isaac Robinson: 1080p, [00:04:00] a whole minute long. We've got light reflecting in puddles. That's reflective. Reminds me of those RTX demonstrations for next generation video games, such as Cyberpunk, but with better graphics. You can see some issues in the background if you look closely, but they're kind of, as with a lot of these models, the issues tend to be things that people aren't going to pay attention to unless they're looking for.[00:04:24] Isaac Robinson: In the same way that like six fingers on a hand. You're not going to notice is a giveaway unless you're looking for it. So yeah, as we said, SORA does not have a paper. So we're going to be filling it in with context from the rest of the computer vision scene attempting to replicate these efforts. So the first step, you have an LLM caption, a huge amount of videos.[00:04:48] Isaac Robinson: This, this is a trick that they introduced in Dolly 3, where they train a image captioning model to just generate very high quality captions for a huge corpus and then train a diffusion model [00:05:00] on that. Their Sora and their application efforts also show a bunch of other steps that are necessary for good video generation.[00:05:09] Isaac Robinson: Including filtering by aesthetic score and filtering by making sure the videos have enough motion. So they're not just like kind of the generators not learning to just generate static frames. So. Then we encode our video into a series of space time latents. Once again, SORA, very sparse in details.[00:05:29] Isaac Robinson: So the replication related works, OpenSORA actually uses a MAG VIT V2 itself to do this, but swapping out the discretization step with a classic VAE autoencoder framework. They show that there's a lot of benefit from getting the temporal compression, which makes a lot of sense as the Each sequential frames and videos have mostly redundant information.[00:05:53] Isaac Robinson: So by compressing against, compressing in the temporal space, you allow the latent to hold [00:06:00] a lot more semantic information while avoiding that duplicate. So, we've got our spacetime latents. Possibly via, there's some 3D VAE, presumably a MAG VATV2 and then you throw it into a diffusion transformer.[00:06:19] Isaac Robinson: So I think it's personally interesting to note that OpenSORA is using a MAG VATV2, which originally used an autoregressive transformer decoder to model the latent space, but is now using a diffusion diffusion transformer. So it's still a transformer happening. Just the question is like, is it?[00:06:37] Isaac Robinson: Parameterizing the stochastic differential equation is, or parameterizing a conditional distribution via autoregression. It's also it's also worth noting that most diffusion models today, the, the very high performance ones are switching away from the classic, like DDPM denoising diffusion probability modeling framework to rectified flows.[00:06:57] Isaac Robinson: Rectified flows have a very interesting property that as [00:07:00] they converge, they actually get closer to being able to be sampled with a single step. Which means that in practice, you can actually generate high quality samples much faster. Major problem of DDPM and related models for the past four years is just that they require many, many steps to generate high quality samples.[00:07:22] Isaac Robinson: So, and naturally, the third step is throwing lots of compute at the problem. So I didn't, I never figured out how to manage to get this video to loop, but we see very little compute, medium compute, lots of compute. This is so interesting because the the original diffusion transformer paper from Facebook actually showed that, in fact, the specific hyperparameters of the transformer didn't really matter that much.[00:07:48] Isaac Robinson: What mattered was that you were just increasing the amount of compute that the model had. So, I love how in the, once again, little blog posts, they don't even talk about [00:08:00] like the specific hyperparameters. They say, we're using a diffusion transformer, and we're
Happy holidays! We’ll be sharing snippets from Latent Space LIVE! through the break bringing you the best of 2024 from friends of the pod!For NeurIPS last year we did our standard conference podcast coverage interviewing selected papers (that we have now also done for ICLR and ICML), however we felt that we could be doing more to help AI Engineers 1) get more industry-relevant content, and 2) recap 2024 year in review from experts. As a result, we organized the first Latent Space LIVE!, our first in person miniconference, at NeurIPS 2024 in Vancouver. For our opening keynote, we could think of no one better to cover 'The State of AI Startups' than our friend Sarah Guo (AI superinvestor, founder of Conviction, host of No Priors!) and Pranav Reddy (Conviction partner) to share their takes on how the AI landscape evolved in 2024 examine the evolving AI landscape and what it means for startups, enterprises, and the industry as a whole! They completely understood the assignment.Recorded live with 200+ in-person and 2200+ online attendees at NeurIPS 2024, this keynote kicks off our mini-conference series exploring different domains of AI development in 2024. Enjoy!LinksSlides: https://x.com/saranormous/status/1866933642401886707Sarh Guo: https://x.com/saranormousPranav Reddy: https://x.com/prnvrdyFull Video on YouTubeWant more content like this? Like and subscribe to stay updated on our latest talks, interviews, and podcasts. Get full access to Latent Space at www.latent.space/subscribe
Our second podcast guest ever in March 2023 was Varun Mohan, CEO of Codeium; at the time, they had around 10,000 users and how they vowed to keep their autocomplete free forever: Today, over a million developers use their products, they still have their free tier, and they recently launched Windsurf, an AI IDE. Chapters* 00:00:00: Introductions & Catchup* 00:03:52: Why they created Windsurf* 00:05:52: Limitations of VS Code* 00:10:12: Evaluation methods for Cascade and Windsurf* 00:16:15: Listener questions about Windsurf launch* 00:20:30: Remote execution and security concerns* 00:25:18: Evolution of Codeium's strategy* 00:28:29: Cascade and its capabilities* 00:33:12: Multi-agent systems* 00:37:02: Areas of improvement for Windsurf* 00:39:12: Building an enterprise-first company* 00:42:01: Copilot for X, AI UX, and Enterprise AI blog posts Get full access to Latent Space at www.latent.space/subscribe
Regular tickets are now sold out for Latent Space LIVE! at NeurIPS! We have just announced our last speaker and newest track, friend of the pod Nathan Lambert who will be recapping 2024 in Reasoning Models like o1! We opened up a handful of late bird tickets for those who are deciding now — use code DISCORDGANG if you need it. See you in Vancouver!We’ve been sitting on our ICML recordings for a while (from today’s first-ever SOLO guest cohost, Brittany Walker), and in light of Sora Turbo’s launch (blogpost, tutorials) today, we figured it would be a good time to drop part one which had been gearing up to be a deep dive into the state of generative video worldsim, with a seamless transition to vision (the opposite modality), and finally robots (their ultimate application).Sora, Genie, and the field of Generative Video World SimulatorsBill Peebles, author of Diffusion Transformers, gave his most recent Sora talk at ICML, which begins our episode:* William (Bill) Peebles - SORA (slides)Something that is often asked about Sora is how much inductive biases were introduced to achieve these results. Bill references the same principles brought by Hyung Won Chung from the o1 team - “sooner or later those biases come back to bite you”.We also recommend these reads from throughout 2024 on Sora.* Lilian Weng’s literature review of Video Diffusion Models* Sora API leak* Estimates of 100k-700k H100s needed to serve Sora (not Turbo)* Artist guides on using Sora for professional storytellingGoogle DeepMind had a remarkably strong presence at ICML on Video Generation Models, winning TWO Best Paper awards for:* Genie: Generative Interactive Environments (covered in oral, poster, and workshop)* VideoPoet: A Large Language Model for Zero-Shot Video Generation (see website)We end this part by taking in Tali Dekel’s talk on The Future of Video Generation: Beyond Data and Scale.Part 2: Generative Modeling and DiffusionSince 2023, Sander Dieleman’s perspectives (blogpost, tweet) on diffusion as “spectral autoregression in the frequency domain” while working on Imagen and Veo have caught the public imagination, so we highlight his talk:* Wading through the noise: an intuitive look at diffusion modelsThen we go to Ben Poole for his talk on Inferring 3D Structure with 2D Priors, including his work on NeRFs and DreamFusion:Then we investigate two flow matching papers - one from the Flow Matching co-authors - Ricky T. Q. Chen (FAIR, Meta)And how it is implemented in Stable Diffusion 3 with Scaling Rectified Flow Transformers for High-Resolution Image Synthesis Our last hit on Diffusion is a couple of oral presentations on speech, which we leave you to explore via our audio podcast* NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models* Speech Self-Supervised Learning Using Diffusion Model Synthetic DataPart 3: VisionThe ICML Test of Time winner was DeCAF, which Trevor Darrell notably called “the OG vision foundation model”.Lucas Beyer’s talk on “Vision in the age of LLMs — a data-centric perspective” was also well received online, and he talked about his journey from Vision Transformers to PaliGemma.We give special honorable mention to MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark.Part 4: Reinforcement Learning and RoboticsWe segue vision into robotics with the help of Ashley Edwards, whose work on both the Gato and the Genie teams at Deepmind is summarized in Learning actions, policies, rewards, and environments from videos alone.Brittany highlighted two poster session papers:* Behavior Generation with Latent Actions* We also recommend Lerrel Pinto’s On Building General-Purpose Robots* PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMsHowever we must give the lion’s share of space to Chelsea Finn, now founder of Physical Intelligence, who gave FOUR talks on* "What robots have taught me about machine learning"* developing robot generalists* robots that adapt autonomously* how to give feedback to your language model* special mention to PI colleague Sergey Levine on Robotic Foundation ModelsWe end the podcast with a position paper that links generative environments and RL/robotics: Automatic Environment Shaping is the Next Frontier in RL.Timestamps* [00:00:00] Intros* [00:02:43] Sora - Bill Peebles* [00:44:52] Genie: Generative Interactive Environments* [01:00:17] Genie interview* [01:12:33] VideoPoet: A Large Language Model for Zero-Shot Video Generation* [01:30:51] VideoPoet interview - Dan Kondratyuk* [01:42:00] Tali Dekel - The Future of Video Generation: Beyond Data and Scale.* [02:27:07] Sander Dieleman - Wading through the noise: an intuitive look at diffusion models* [03:06:20] Ben Poole - Inferring 3D Structure with 2D Priors* [03:30:30] Ricky Chen - Flow Matching* [04:00:03] Patrick Esser - Stable Diffusion 3* [04:14:30] NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models* [04:27:00] Speech Self-Supervised Learning Using Diffusion Model Synthetic Data* [04:39:00] ICML Test of Time winner: DeCAF* [05:03:40] Lucas Beyer: “Vision in the age of LLMs — a data-centric perspective”* [05:42:00] Ashley Edwards: Learning actions, policies, rewards, and environments from videos alone.* [06:03:30] Behavior Generation with Latent Actions interview* [06:09:52] Chelsea Finn: "What robots have taught me about machine learning"* [06:56:00] Position: Automatic Environment Shaping is the Next Frontier in RL Get full access to Latent Space at www.latent.space/subscribe
The full schedule for Latent Space LIVE! at NeurIPS has been announced, featuring Best of 2024 overview talks for the AI Startup Landscape, Computer Vision, Open Models, Transformers Killers, Synthetic Data, Agents, and Scaling, and speakers from Sarah Guo of Conviction, Roboflow, AI2/Meta, Recursal/Together, HuggingFace, OpenHands and SemiAnalysis. Join us for the IRL event/Livestream! Alessio will also be holding a meetup at AWS Re:Invent in Las Vegas this Wednesday. See our new Events page for dates of AI Engineer Summit, Singapore, and World’s Fair in 2025. LAST CALL for questions for our big 2024 recap episode! Submit questions and messages on Speakpipe here for a chance to appear on the show!When we first observed that GPT Wrappers are Good, Actually, we did not even have Bolt on our radar. Since we recorded our Anthropic episode discussing building Agents with the new Claude 3.5 Sonnet, Bolt.new (by Stackblitz) has easily cleared the $8m ARR bar, repeating and accelerating its initial $4m feat.There are very many AI code generators and VS Code forks out there, but Bolt probably broke through initially because of its incredible zero shot low effort app generation:But as we explain in the pod, Bolt also emphasized deploy (Netlify)/ backend (Supabase)/ fullstack capabilities on top of Stackblitz’s existing WebContainer full-WASM-powered-developer-environment-in-the-browser tech. Since then, the team has been shipping like mad (with weekly office hours), with bugfixing, full screen, multi-device, long context, diff based edits (using speculative decoding like we covered in Inference, Fast and Slow).All of this has captured the imagination of low/no code builders like Greg Isenberg and many others on YouTube/TikTok/Reddit/X/Linkedin etc:Just as with Fireworks, our relationship with Bolt/Stackblitz goes a bit deeper than normal - swyx advised the launch and got a front row seat to this epic journey, as well as demoed it with Realtime Voice at the recent OpenAI Dev Day. So we are very proud to be the first/closest to tell the full open story of Bolt/Stackblitz!Flow Engineering + Qodo/AlphaCodium UpdateIn year 2 of the pod we have been on a roll getting former guests to return as guest cohosts (Harrison Chase, Aman Sanger, Jon Frankle), and it was a pleasure to catch Itamar Friedman back on the pod, giving us an update on all things Qodo and Testing Agents from our last catchup a year and a half ago:Qodo (they renamed in September) went viral in early January this year with AlphaCodium (paper here, code here) beating DeepMind’s AlphaCode with high efficiency:With a simple problem solving code agent:* The first step is to have the model reason about the problem. They describe it using bullet points and focus on the goal, inputs, outputs, rules, constraints, and any other relevant details.* Then, they make the model reason about the public tests and come up with an explanation of why the input leads to that particular output. * The model generates two to three potential solutions in text and ranks them in terms of correctness, simplicity, and robustness. * Then, it generates more diverse tests for the problem, covering cases not part of the original public tests. * Iteratively, pick a solution, generate the code, and run it on a few test cases. * If the tests fail, improve the code and repeat the process until the code passes every test.swyx has previously written similar thoughts on types vs tests for putting bounds on program behavior, but AlphaCodium extends this to AI generated tests and code.More recently, Itamar has also shown that AlphaCodium’s techniques also extend well to the o1 models:Making Flow Engineering a useful technique to improve code model performance on every model. This is something we see AI Engineers uniquely well positioned to do compared to ML Engineers/Researchers.Full Video PodcastLike and subscribe!Show Notes* Itamar* Qodo* First episode* Eric* Bolt* StackBlitz* Thinkster* AlphaCodium* WebContainersChapters* 00:00:00 Introductions & Updates* 00:06:01 Generic vs. Specific AI Agents* 00:07:40 Maintaining vs Creating with AI* 00:17:46 Human vs Agent Computer Interfaces* 00:20:15 Why Docker doesn't work for Bolt* 00:24:23 Creating Testing and Code Review Loops* 00:28:07 Bolt's Task Breakdown Flow* 00:31:04 AI in Complex Enterprise Environments* 00:41:43 AlphaCodium* 00:44:39 Strategies for Breaking Down Complex Tasks* 00:45:22 Building in Open Source* 00:50:35 Choosing a product as a founder* 00:59:03 Reflections on Bolt Success* 01:06:07 Building a B2C GTM* 01:18:11 AI Capabilities and Pricing Tiers* 01:20:28 What makes Bolt unique* 01:23:07 Future Growth and Product Development* 01:29:06 Competitive Landscape in AI Engineering* 01:30:01 Advice to Founders and Embracing AI* 01:32:20 Having a baby and completing an Iron ManTranscriptAlessio [00:00:00]: Hey everyone, welcome to the Latent Space Podcast. This is Alessio, partner and CTO at Decibel Partners, and I'm joined by my co-host Swyx, founder of Smol.ai.Swyx [00:00:12]: Hey, and today we're still in our sort of makeshift in-between studio, but we're very delighted to have a former returning guest host, Itamar. Welcome back.Itamar [00:00:21]: Great to be here after a year or more. Yeah, a year and a half.Swyx [00:00:24]: You're one of our earliest guests on Agents. Now you're CEO co-founder of Kodo. Right. Which has just been renamed. You also raised a $40 million Series A, and we can get caught up on everything, but we're also delighted to have our new guest, Eric. Welcome.Eric [00:00:42]: Thank you. Excited to be here. Should I say Bolt or StackBlitz?Swyx [00:00:45]: Like, is it like its own company now or?Eric [00:00:47]: Yeah. Bolt's definitely bolt.new. That's the thing that we're probably the most known for, I imagine, at this point.Swyx [00:00:54]: Which is ridiculous to say because you were working at StackBlitz for so long.Eric [00:00:57]: Yeah. I mean, within a week, we were doing like double the amount of traffic. And StackBlitz had been online for seven years, and we were like, what? But anyways, yeah. So we're StackBlitz, the company behind bolt.new. If you've heard of bolt.new, that's our stuff. Yeah.Swyx [00:01:12]: Yeah.Itamar [00:01:13]: Excellent. I see, by the way, that the founder mode, you need to know to capture opportunities. So kudos on doing that, right? You're working on some technology, and then suddenly you can exploit that to a new world. Yeah.Eric [00:01:24]: Totally. And I think, well, not to jump, but 100%, I mean, a couple of months ago, we had the idea for Bolt earlier this year, but we haven't really shared this too much publicly. But we actually had tried to build it with some of those state-of-the-art models back in January, February, you can kind of imagine which, and they just weren't good enough to actually do the code generation where the code was accurate and it was fast and whatever have you without a ton of like rag, but then there was like issues with that. So we put it on the shelf and then we got kind of a sneak peek of some of the new models that have come out in the past couple of months now. And so once we saw that, once we actually saw the code gen from it, we were like, oh my God, like, okay, we can build a product around this. And so that was really the impetus of us building the thing. But with that, it was StackBlitz, the core StackBlitz product the past seven years has been an IDE for developers. So the entire user experience flow we've built up just didn't make sense. And so when we kind of went out to build Bolt, we just thought, you know, if we were inventing our product today, what would the interface look like given what is now possible with the AI code gen? And so there's definitely a lot of conversations we had internally, but you know, just kind of when we logically laid it out, we were like, yeah, I think it makes sense to just greenfield a new thing and let's see what happens. If it works great, then we'll figure it out. If it doesn't work great, then it'll get deleted at some point. So that's kind of how it actually came to be.Swyx [00:02:49]: I'll mention your background a little bit. You were also founder of Thinkster before you started StackBlitz. So both of you are second time founders. Both of you have sort of re-founded your company recently. Yours was more of a rename. I think a slightly different direction as well. And then we can talk about both. Maybe just chronologically, should we get caught up on where Kodo is first and then you know, just like what people should know since the last pod? Sure.Itamar [00:03:12]: The last pod was two months after we launched and we basically had the vision that we talked about. The idea that software development is about specification, test and code, etc. We are more on the testing part as in essence, we think that if you solve testing, you solve software development. The beautiful chart that we'll put up on screen. And testing is a really big field, like there are many dimensions, unit testing, the level of the component, how big it is, how large it is. And then there is like different type of testing, is it regression or smoke or whatever. So back then we only had like one ID extension with unit tests as in focus. One and a half year later, first ID extension supports more type of testing as context aware. We index local, local repos, but also 10,000s of repos for Fortune 500 companies. We have another agent, another tool that is called, the pure agent is the open source and the commercial one is CodoMerge. And then we have another open source called CoverAgent, which is not yet a commercial product coming very soon. It's very impressive. It could be that already people are approving automated pull requests that they don't even aware in really big open sources. So once we have enough of these, we will also launch another agent. So for the first one and a half year, what we did is grew in our offering and mostly on the sid
We have announced our first speaker, friend of the show Dylan Patel, and topic slates for Latent Space LIVE! at NeurIPS. Sign up for IRL/Livestream and to debate!We are still taking questions for our next big recap episode! Submit questions and messages on Speakpipe here for a chance to appear on the show!The vibe shift we observed in July - in favor of Claude 3.5 Sonnet, first introduced in June — has been remarkably long lived and persistent, surviving multiple subsequent updates of 4o, o1 and Gemini versions, for Anthropic’s Claude to end 2024 as the preferred model for AI Engineers and even being the exclusive choice for new code agents like bolt.new (our next guest on the pod!), which unlocked so much performance from Claude Sonnet that it went from $0 to $4m ARR in 4 weeks when it launched last month.Anthropic has now raised an additional $4b from Amazon and made an incredibly well received update of Claude 3.5 Sonnet (and Haiku), making significant improvements in performance over its predecessors:Solving SWE-BenchAs part of the October Sonnet release, Anthropic teased a blink-and-you’ll miss it result:The updated Claude 3.5 Sonnet shows wide-ranging improvements on industry benchmarks, with particularly strong gains in agentic coding and tool use tasks. On coding, it improves performance on SWE-bench Verified from 33.4% to 49.0%, scoring higher than all publicly available models—including reasoning models like OpenAI o1-preview and specialized systems designed for agentic coding. It also improves performance on TAU-bench, an agentic tool use task, from 62.6% to 69.2% in the retail domain, and from 36.0% to 46.0% in the more challenging airline domain. The new Claude 3.5 Sonnet offers these advancements at the same price and speed as its predecessor.This was followed up by a blogpost a week later from today’s guest, Erik Schluntz, the engineer who implemented and scored this SOTA result using a simple, non-overengineered version of the SWE-Agent framework (you can see the submissions here). We have previously covered the SWE-Bench story extensively:* Speaking with SWEBench/SWEAgent authors at ICLR* Speaking with Cosine Genie, the previous SOTA (43.8%) on SWEBench Verified (with brief update at DevDay 2024)* Speaking with Shunyu Yao on SWEBench and the ReAct paradigm driving SWE-AgentOne of the notable inclusions in this blogpost are the tools that Erik decided to give Claude, e.g. the “Edit Tool”:The tools teased in the SWEBench submission/blogpost were then polished up and released with Computer Use…And you can also see even more computer use tools given in the new Model Context Protocol servers:Claude Computer UseBecause it is one of the best received AI releases of the year, we recommend watching the 2 minute Computer Use intro (and related demos) in its entirety:Eric also worked on Claude’s function calling, tool use, and computer use APIs, so we discuss that in the episode.Erik [00:53:39]: With computer use, just give the thing a browser that's logged into what you want to integrate with, and it's going to work immediately. And I see that reduction in friction as being incredibly exciting. Imagine a customer support team where, okay, hey, you got this customer support bot, but you need to go integrate it with all these things. And you don't have any engineers on your customer support team. But if you can just give the thing a browser that's logged into your systems that you need it to have access to, now, suddenly, in one day, you could be up and rolling with a fully integrated customer service bot that could go do all the actions you care about. So I think that's the most exciting thing for me about computer use, is reducing that friction of integrations to almost zero.As you’ll see, this is very top of mind for Erik as a former Robotics founder who’s company basically used robots to interface with human physical systems like elevators.Full Video episodePlease like and subscribe!Show Notes* Eric Schluntz* “Raising the bar on SWE-Bench Verified”* Cobalt Robotics* SWE-Bench* SWE-Bench Verified* Human Eval & other benchmarks* Anthropic Workbench* Aider* Cursor* Fireworks AI* E2B* Amanda Askell* Toyota Research* Physical Intelligence (Pi)* Chelsea Finn* Josh Albrecht* Eric Jang* 1X* Dust* Cosine Episode* Bolt* Adept Episode* TauBench* LMSys EpisodeTimestamps* [00:00:00] Introductions* [00:03:39] What is SWE-Bench?* [00:12:22] SWE-Bench vs HumanEval vs others* [00:15:21] SWE-Agent architecture and runtime* [00:21:18] Do you need code indexing?* [00:24:50] Giving the agent tools* [00:27:47] Sandboxing for coding agents* [00:29:16] Why not write tests?* [00:30:31] Redesigning engineering tools for LLMs* [00:35:53] Multi-agent systems* [00:37:52] Why XML so good?* [00:42:57] Thoughts on agent frameworks* [00:45:12] How many turns can an agent do?* [00:47:12] Using multiple model types* [00:51:40] Computer use and agent use cases* [00:59:04] State of AI robotics* [01:04:24] Robotics in manufacturing* [01:05:01] Hardware challenges in robotics* [01:09:21] Is self-driving a good business?TranscriptAlessio [00:00:00]: Hey everyone, welcome to the Latent Space Podcast. This is Alessio, partner and CTO at Decibel Partners. And today we're in the new studio with my usual co-host, Shawn from Smol AI.Swyx [00:00:14]: Hey, and today we're very blessed to have Erik Schluntz from Anthropic with us. Welcome.Erik [00:00:19]: Hi, thanks very much. I'm Erik Schluntz. I'm a member of technical staff at Anthropic, working on tool use, computer use, and Swebench.Swyx [00:00:27]: Yeah. Well, how did you get into just the whole AI journey? I think you spent some time at SpaceX as well? Yeah. And robotics. Yeah. There's a lot of overlap between like the robotics people and the AI people, and maybe like there's some interlap or interest between language models for robots right now. Maybe just a little bit of background on how you got to where you are. Yeah, sure.Erik [00:00:50]: I was at SpaceX a long time ago, but before joining Anthropic, I was the CTO and co-founder of Cobalt Robotics. We built security and inspection robots. These are sort of five foot tall robots that would patrol through an office building or a warehouse looking for anything out of the ordinary. Very friendly, no tasers or anything. We would just sort of call a remote operator if we saw anything. We have about 100 of those out in the world, and had a team of about 100. We actually got acquired about six months ago, but I had left Cobalt about a year ago now, because I was starting to get a lot more excited about AI. I had been writing a lot of my code with things like Copilot, and I was like, wow, this is actually really cool. If you had told me 10 years ago that AI would be writing a lot of my code, I would say, hey, I think that's AGI. And so I kind of realized that we had passed this level, like, wow, this is actually really useful for engineering work. That got me a lot more excited about AI and learning about large language models. So I ended up taking a sabbatical and then doing a lot of reading and research myself and decided, hey, I want to go be at the core of this and joined Anthropic.Alessio [00:01:53]: And why Anthropic? Did you consider other labs? Did you consider maybe some of the robotics companies?Erik [00:02:00]: So I think at the time I was a little burnt out of robotics, and so also for the rest of this, any sort of negative things I say about robotics or hardware is coming from a place of burnout, and I reserve my right to change my opinion in a few years. Yeah, I looked around, but ultimately I knew a lot of people that I really trusted and I thought were incredibly smart at Anthropic, and I think that was the big deciding factor to come there. I was like, hey, this team's amazing. They're not just brilliant, but sort of like the most nice and kind people that I know, and so I just felt like I could be a really good culture fit. And ultimately, I do care a lot about AI safety and making sure that I don't want to build something that's used for bad purposes, and I felt like the best chance of that was joining Anthropic.Alessio [00:02:39]: And from the outside, these labs kind of look like huge organizations that have these obscureSwyx [00:02:44]: ways to organize.Alessio [00:02:45]: How did you get, you joined Anthropic, did you already know you were going to work on of the stuff you publish or you kind of join and then you figure out where you land? I think people are always curious to learn more.Erik [00:02:57]: Yeah, I've been very happy that Anthropic is very bottoms up and sort of very sort of receptive to whatever your interests are. And so I joined sort of being very transparent of like, hey, I'm most excited about code generation and AI that can actually go out and sort of touch the world or sort of help people build things. And, you know, those weren't my initial initial projects. I also came in and said, hey, I want to do the most valuable possible thing for this company and help Anthropic succeed. And, you know, like, let me find the balance of those. So I was working on lots of things at the beginning, you know, function calling, tool use. And then sort of as it became more and more relevant, I was like, oh, hey, like, let's it's time to go work on encoding agents and sort of started looking at SWE-Bench as sort of a really good benchmark for that.Swyx [00:03:39]: So let's get right into SWE-Bench. That's one of the many claims to fame. I feel like there's just been a series of releases related with Cloud 3.5 Sonnet around about two or three months ago, 3.5 Sonnet came out and it was it was a step ahead in terms of a lot of people immediately fell in love with it for coding. And then last month you released a new updated version of Cloud Sonnet. We're not going to talk about the training for that because that's still confidential. But I think Anthropic's done a really good job, like applying the model to different things.
We have a full slate of upcoming events: AI Engineer London, AWS Re:Invent in Las Vegas, and now Latent Space LIVE! at NeurIPS in Vancouver and online. Sign up to join and speak!We are still taking questions for our next big recap episode! Submit questions and messages on Speakpipe here for a chance to appear on the show!We try to stay close to the inference providers as part of our coverage, as our podcasts with Together AI and Replicate will attest: However one of the most notable pull quotes from our very well received Braintrust episode was his opinion that open source model adoption has NOT gone very well and is actually declining in relative market share terms (it is of course increasing in absolute terms):Today’s guest, Lin Qiao, would wholly disagree. Her team of Pytorch/GPU experts are wholly dedicated toward helping you serve and finetune the full stack of open source models from Meta and others, across all modalities (Text, Audio, Image, Embedding, Vision-understanding), helping customers like Cursor and Hubspot scale up open source model inference both rapidly and affordably.Fireworks has emerged after its successive funding rounds with top tier VCs as one of the leaders of the Compound AI movement, a term first coined by the Databricks/Mosaic gang at Berkeley AI and adapted as “Composite AI” by Gartner:Replicating o1We are the first podcast to discuss Fireworks’ f1, their proprietary replication of OpenAI’s o1. This has become a surprisingly hot area of competition in the past week as both Nous Forge and Deepseek r1 have launched competitive models.Full Video PodcastLike and subscribe!Timestamps* 00:00:00 Introductions* 00:02:08 Pre-history of Fireworks and PyTorch at Meta* 00:09:49 Product Strategy: From Framework to Model Library* 00:13:01 Compound AI Concept and Industry Dynamics* 00:20:07 Fireworks' Distributed Inference Engine* 00:22:58 OSS Model Support and Competitive Strategy* 00:29:46 Declarative System Approach in AI* 00:31:00 Can OSS replicate o1?* 00:36:51 Fireworks f1* 00:41:03 Collaboration with Cursor and Speculative Decoding* 00:46:44 Fireworks quantization (and drama around it)* 00:49:38 Pricing Strategy* 00:51:51 Underrated Features of Fireworks Platform* 00:55:17 HiringTranscriptAlessio [00:00:00]: Hey everyone, welcome to the Latent Space Podcast. This is Alessio, partner at CTO at Danceable Partners, and I'm joined by my co-host, Swyx founder, Osmalayar.Swyx [00:00:11]: Hey, and today we're in a very special studio inside the Fireworks office with Lin Qiang, CEO of Fireworks. Welcome. Yeah.Lin [00:00:20]: Oh, you should welcome us.Swyx [00:00:21]: Yeah, welcome. Yeah, thanks for having us. It's unusual to be in the home of a startup, but it's also, I think our relationship is a bit unusual compared to all our normal guests. Definitely.Lin [00:00:34]: Yeah. I'm super excited to talk about very interesting topics in that space with both of you.Swyx [00:00:41]: You just celebrated your two-year anniversary yesterday.Lin [00:00:43]: Yeah, it's quite a crazy journey. We circle around and share all the crazy stories across these two years, and it has been super fun. All the way from we experienced Silicon Valley bank run to we delete some data that shouldn't be deleted operationally. We went through a massive scale where we actually are busy getting capacity to, yeah, we learned to kind of work with it as a team with a lot of brilliant people across different places to join a company. It has really been a fun journey.Alessio [00:01:24]: When you started, did you think the technical stuff will be harder or the bank run and then the people side? I think there's a lot of amazing researchers that want to do companies and it's like the hardest thing is going to be building the product and then you have all these different other things. So, were you surprised by what has been your experience the most?Lin [00:01:42]: Yeah, to be honest with you, my focus has always been on the product side and then after the product goes to market. And I didn't realize the rest has been so complicated, operating a company and so on. But because I don't think about it, I just kind of manage it. So it's done. I think I just somehow don't think about it too much and solve whatever problem coming our way and it worked.Swyx [00:02:08]: So let's, I guess, let's start at the pre-history, the initial history of Fireworks. You ran the PyTorch team at Meta for a number of years and we previously had Sumit Chintal on and I think we were just all very interested in the history of GenEI. Maybe not that many people know how deeply involved Faire and Meta were prior to the current GenEI revolution.Lin [00:02:35]: My background is deep in distributed system, database management system. And I joined Meta from the data side and I saw this tremendous amount of data growth, which cost a lot of money and we're analyzing what's going on. And it's clear that AI is driving all this data generation. So it's a very interesting time because when I joined Meta, Meta is going through ramping down mobile-first, finishing the mobile-first transition and then starting AI-first. And there's a fundamental reason about that sequence because mobile-first gave a full range of user engagement that has never existed before. And all this user engagement generated a lot of data and this data power AI. So then the whole entire industry is also going through, falling through this same transition. When I see, oh, okay, this AI is powering all this data generation and look at where's our AI stack. There's no software, there's no hardware, there's no people, there's no team. I want to dive up there and help this movement. So when I started, it's very interesting industry landscape. There are a lot of AI frameworks. It's a kind of proliferation of AI frameworks happening in the industry. But all the AI frameworks focus on production and they use a very certain way of defining the graph of neural network and then use that to drive the model iteration and productionization. And PyTorch is completely different. So they could also assume that he was the user of his product. And he basically says, researchers face so much pain using existing AI frameworks, this is really hard to use and I'm going to do something different for myself. And that's the origin story of PyTorch. PyTorch actually started as the framework for researchers. They don't care about production at all. And as they grow in terms of adoption, so the interesting part of AI is research is the top of our normal production. There are so many researchers across academic, across industry, they innovate and they put their results out there in open source and that power the downstream productionization. So it's brilliant for MATA to establish PyTorch as a strategy to drive massive adoption in open source because MATA internally is a PyTorch shop. So it creates a flying wheel effect. So that's kind of a strategy behind PyTorch. But when I took on PyTorch, it's kind of at Caspo, MATA established PyTorch as the framework for both research and production. So no one has done that before. And we have to kind of rethink how to architect PyTorch so we can really sustain production workload, the stability, reliability, low latency, all this production concern was never a concern before. Now it's a concern. And we actually have to adjust its design and make it work for both sides. And that took us five years because MATA has so many AI use cases, all the way from ranking recommendation as powering the business top line or as ranking newsfeed, video ranking to site integrity detect bad content automatically using AI to all kinds of effects, translation, image classification, object detection, all this. And also across AI running on the server side, on mobile phones, on AI VR devices, the wide spectrum. So by the time we actually basically managed to support AI across ubiquitous everywhere across MATA. But interestingly, through open source engagement, we work with a lot of companies. It is clear to us like this industry is starting to take on AI first transition. And of course, MATA's hyperscale always go ahead of industry. And it feels like when we start this AI journey at MATA, there's no software, no hardware, no team. For many companies we engage with through PyTorch, we feel the pain. That's the genesis why we feel like, hey, if we create fireworks and support industry going through this transition, it will be a huge amount of impact. Of course, the problem that the industry is facing will not be the same as MATA. MATA is so big, right? So it's kind of skewed towards extreme scale and extreme optimization in the industry will be different. But we feel like we have the technical chop and we've seen a lot. We'll look to kind of drive that. So yeah, so that's how we started.Swyx [00:06:58]: When you and I chatted about the origins of fireworks, it was originally envisioned more as a PyTorch platform, and then later became much more focused on generative AI. Is that fair to say? What was the customer discovery here?Lin [00:07:13]: Right. So I would say our initial blueprint is we should build a PyTorch cloud because a PyTorch library and there's no SaaS platform to enable AI workloads.Swyx [00:07:26]: Even in 2022, it's interesting.Lin [00:07:28]: I would not say absolutely no, but cloud providers have some of those, but it's not first class citizen, right? At 2022, there's still like TensorFlow is massively in production. And this is all pre-gen AI, and PyTorch is kind of getting more and more adoption. But there's no PyTorch-first SaaS platform existing. At the same time, we are also a very pragmatic set of people. We really want to make sure from the get-go, we get really, really close to customers. We understand their use case, we understand their pain points, we understand the value we deliver to them. So we want to take a different approach instead of building a horizontal PyTorch cloud. We want to bu
Alessio will be at AWS re:Invent next week and hosting a casual coffee meetup on Wednesday, RSVP here! And subscribe to our calendar for our Singapore, NeurIPS, and all upcoming meetups!We are still taking questions for our next big recap episode! Submit questions and messages on Speakpipe here for a chance to appear on the show!If you've been following the AI agents space, you have heard of Lindy AI; while founder Flo Crivello is hesitant to call it "blowing up," when folks like Andrew Wilkinson start obsessing over your product, you're definitely onto something.In our latest episode, Flo walked us through Lindy's evolution from late 2022 to now, revealing some design choices about agent platform design that go against conventional wisdom in the space.The Great Reset: From Text Fields to RailsRemember late 2022? Everyone was "LLM-pilled," believing that if you just gave a language model enough context and tools, it could do anything. Lindy 1.0 followed this pattern:* Big prompt field ✅* Bunch of tools ✅* Prayer to the LLM gods ✅Fast forward to today, and Lindy 2.0 looks radically different. As Flo put it (~17:00 in the episode): "The more you can put your agent on rails, one, the more reliable it's going to be, obviously, but two, it's also going to be easier to use for the user."Instead of a giant, intimidating text field, users now build workflows visually:* Trigger (e.g., "Zendesk ticket received")* Required actions (e.g., "Check knowledge base")* Response generationThis isn't just a UI change - it's a fundamental rethinking of how to make AI agents reliable. As Swyx noted during our discussion: "Put Shoggoth in a box and make it a very small, minimal viable box. Everything else should be traditional if-this-then-that software."The Surprising Truth About Model LimitationsHere's something that might shock folks building in the space: with Claude 3.5 Sonnet, the model is no longer the bottleneck. Flo's exact words (~31:00): "It is actually shocking the extent to which the model is no longer the limit. It was the limit a year ago. It was too expensive. The context window was too small."Some context: Lindy started when context windows were 4K tokens. Today, their system prompt alone is larger than that. But what's really interesting is what this means for platform builders:* Raw capabilities aren't the constraint anymore* Integration quality matters more than model performance* User experience and workflow design are the new bottlenecksThe Search Engine Parallel: Why Horizontal Platforms Might WinOne of the spiciest takes from our conversation was Flo's thesis on horizontal vs. vertical agent platforms. He draws a fascinating parallel to search engines (~56:00):"I find it surprising the extent to which a horizontal search engine has won... You go through Google to search Reddit. You go through Google to search Wikipedia... search in each vertical has more in common with search than it does with each vertical."His argument: agent platforms might follow the same pattern because:* Agents across verticals share more commonalities than differences* There's value in having agents that can work together under one roof* The R&D cost of getting agents right is better amortized across use casesThis might explain why we're seeing early vertical AI companies starting to expand horizontally. The core agent capabilities - reliability, context management, tool integration - are universal needs.What This Means for BuildersIf you're building in the AI agents space, here are the key takeaways:* Constrain First: Rather than maximizing capabilities, focus on reliable execution within narrow bounds* Integration Quality Matters: With model capabilities plateauing, your competitive advantage lies in how well you integrate with existing tools* Memory Management is Key: Flo revealed they actively prune agent memories - even with larger context windows, not all memories are useful* Design for Discovery: Lindy's visual workflow builder shows how important interface design is for adoptionThe Meta LayerThere's a broader lesson here about AI product development. Just as Lindy evolved from "give the LLM everything" to "constrain intelligently," we might see similar evolution across the AI tooling space. The winners might not be those with the most powerful models, but those who best understand how to package AI capabilities in ways that solve real problems reliably.Full Video PodcastFlo’s talk at AI Engineer SummitChapters* 00:00:00 Introductions * 00:04:05 AI engineering and deterministic software * 00:08:36 Lindys demo* 00:13:21 Memory management in AI agents * 00:18:48 Hierarchy and collaboration between Lindys * 00:21:19 Vertical vs. horizontal AI tools * 00:24:03 Community and user engagement strategies * 00:26:16 Rickrolling incident with Lindy * 00:28:12 Evals and quality control in AI systems * 00:31:52 Model capabilities and their impact on Lindy * 00:39:27 Competition and market positioning * 00:42:40 Relationship between Factorio and business strategy * 00:44:05 Remote work vs. in-person collaboration * 00:49:03 Europe vs US Tech* 00:58:59 Testing the Overton window and free speech * 01:04:20 Balancing AI safety concerns with business innovation Show Notes* Lindy.ai* Rick Rolling* Flo on X* TeamFlow* Andrew Wilkinson* Dust* Poolside.ai* SB1047* Gathertown* Sid Sijbrandij* Matt Mullenweg* Factorio* Seeing Like a StateTranscriptAlessio [00:00:00]: Hey everyone, welcome to the Latent Space Podcast. This is Alessio, partner and CTO at Decibel Partners, and I'm joined by my co-host Swyx, founder of Smol.ai.Swyx [00:00:12]: Hey, and today we're joined in the studio by Florent Crivello. Welcome.Flo [00:00:15]: Hey, yeah, thanks for having me.Swyx [00:00:17]: Also known as Altimore. I always wanted to ask, what is Altimore?Flo [00:00:21]: It was the name of my character when I was playing Dungeons & Dragons. Always. I was like 11 years old.Swyx [00:00:26]: What was your classes?Flo [00:00:27]: I was an elf. I was a magician elf.Swyx [00:00:30]: Well, you're still spinning magic. Right now, you're a solo founder and CEO of Lindy.ai. What is Lindy?Flo [00:00:36]: Yeah, we are a no-code platform letting you build your own AI agents easily. So you can think of we are to LangChain as Airtable is to MySQL. Like you can just pin up AI agents super easily by clicking around and no code required. You don't have to be an engineer and you can automate business workflows that you simply could not automate before in a few minutes.Swyx [00:00:55]: You've been in our orbit a few times. I think you spoke at our Latent Space anniversary. You spoke at my summit, the first summit, which was a really good keynote. And most recently, like we actually already scheduled this podcast before this happened. But Andrew Wilkinson was like, I'm obsessed by Lindy. He's just created a whole bunch of agents. So basically, why are you blowing up?Flo [00:01:16]: Well, thank you. I think we are having a little bit of a moment. I think it's a bit premature to say we're blowing up. But why are things going well? We revamped the product majorly. We called it Lindy 2.0. I would say we started working on that six months ago. We've actually not really announced it yet. It's just, I guess, I guess that's what we're doing now. And so we've basically been cooking for the last six months, like really rebuilding the product from scratch. I think I'll list you, actually, the last time you tried the product, it was still Lindy 1.0. Oh, yeah. If you log in now, the platform looks very different. There's like a ton more features. And I think one realization that we made, and I think a lot of folks in the agent space made the same realization, is that there is such a thing as too much of a good thing. I think many people, when they started working on agents, they were very LLM peeled and chat GPT peeled, right? They got ahead of themselves in a way, and us included, and they thought that agents were actually, and LLMs were actually more advanced than they actually were. And so the first version of Lindy was like just a giant prompt and a bunch of tools. And then the realization we had was like, hey, actually, the more you can put your agent on Rails, one, the more reliable it's going to be, obviously, but two, it's also going to be easier to use for the user, because you can really, as a user, you get, instead of just getting this big, giant, intimidating text field, and you type words in there, and you have no idea if you're typing the right word or not, here you can really click and select step by step, and tell your agent what to do, and really give as narrow or as wide a guardrail as you want for your agent. We started working on that. We called it Lindy on Rails about six months ago, and we started putting it into the hands of users over the last, I would say, two months or so, and I think things really started going pretty well at that point. The agent is way more reliable, way easier to set up, and we're already seeing a ton of new use cases pop up.Swyx [00:03:00]: Yeah, just a quick follow-up on that. You launched the first Lindy in November last year, and you were already talking about having a DSL, right? I remember having this discussion with you, and you were like, it's just much more reliable. Is this still the DSL under the hood? Is this a UI-level change, or is it a bigger rewrite?Flo [00:03:17]: No, it is a much bigger rewrite. I'll give you a concrete example. Suppose you want to have an agent that observes your Zendesk tickets, and it's like, hey, every time you receive a Zendesk ticket, I want you to check my knowledge base, so it's like a RAG module and whatnot, and then answer the ticket. The way it used to work with Lindy before was, you would type the prompt asking it to do that. You check my knowledge base, and so on and so forth. The problem with doing that is that it can always go wrong. You're praying the LLM gods that they will actually invoke y
We are recording our next big recap episode and taking questions! Submit questions and messages on Speakpipe here for a chance to appear on the show!Also subscribe to our calendar for our Singapore, NeurIPS, and all upcoming meetups!In our first ever episode with Logan Kilpatrick we called out the two hottest LLM frameworks at the time: LangChain and Dust. We’ve had Harrison from LangChain on twice (as a guest and as a co-host), and we’ve now finally come full circle as Stanislas from Dust joined us in the studio.After stints at Oracle and Stripe, Stan had joined OpenAI to work on mathematical reasoning capabilities. He describes his time at OpenAI as "the PhD I always wanted to do" while acknowledging the challenges of research work: "You're digging into a field all day long for weeks and weeks, and you find something, you get super excited for 12 seconds. And at the 13 seconds, you're like, 'oh, yeah, that was obvious.' And you go back to digging." This experience, combined with early access to GPT-4's capabilities, shaped his decision to start Dust: "If we believe in AGI and if we believe the timelines might not be too long, it's actually the last train leaving the station to start a company. After that, it's going to be computers all the way down."The History of DustDust's journey can be broken down into three phases:* Developer Framework (2022): Initially positioned as a competitor to LangChain, Dust started as a developer tooling platform. While both were open source, their approaches differed – LangChain focused on broad community adoption and integration as a pure developer experience, while Dust emphasized UI-driven development and better observability that wasn’t just `print` statements.* Browser Extension (Early 2023): The company pivoted to building XP1, a browser extension that could interact with web content. This experiment helped validate user interaction patterns with AI, even while using less capable models than GPT-4.* Enterprise Platform (Current): Today, Dust has evolved into an infrastructure platform for deploying AI agents within companies, with impressive metrics like 88% daily active users in some deployments.The Case for Being HorizontalThe big discussion for early stage companies today is whether or not to be horizontal or vertical. Since models are so good at general tasks, a lot of companies are building vertical products that take care of a workflow end-to-end in order to offer more value and becoming more of “Services as Software”. Dust on the other hand is a platform for the users to build their own experiences, which has had a few advantages:* Maximum Penetration: Dust reports 60-70% weekly active users across entire companies, demonstrating the potential reach of horizontal solutions rather than selling into a single team.* Emergent Use Cases: By allowing non-technical users to create agents, Dust enables use cases to emerge organically from actual business needs rather than prescribed solutions.* Infrastructure Value: The platform approach creates lasting value through maintained integrations and connections, similar to how Stripe's value lies in maintaining payment infrastructure. Rather than relying on third-party integration providers, Dust maintains its own connections to ensure proper handling of different data types and structures.The Vertical ChallengeHowever, this approach comes with trade-offs:* Harder Go-to-Market: As Stan talked about: "We spike at penetration... but it makes our go-to-market much harder. Vertical solutions have a go-to-market that is much easier because they're like, 'oh, I'm going to solve the lawyer stuff.'"* Complex Infrastructure: Building a horizontal platform requires maintaining numerous integrations and handling diverse data types appropriately – from structured Salesforce data to unstructured Notion pages. As you scale integrations, the cost of maintaining them also scales. * Product Surface Complexity: Creating an interface that's both powerful and accessible to non-technical users requires careful design decisions, down to avoiding technical terms like "system prompt" in favor of "instructions." The Future of AI PlatformsStan initially predicted we'd see the first billion-dollar single-person company in 2023 (a prediction later echoed by Sam Altman), but he's now more focused on a different milestone: billion-dollar companies with engineering teams of just 20 people, enabled by AI assistance.This vision aligns with Dust's horizontal platform approach – building the infrastructure that allows small teams to achieve outsized impact through AI augmentation. Rather than replacing entire job functions (the vertical approach), they're betting on augmenting existing workflows across organizations.Full YouTube EpisodeChapters* 00:00:00 Introductions* 00:04:33 Joining OpenAI from Paris* 00:09:54 Research evolution and compute allocation at OpenAI* 00:13:12 Working with Ilya Sutskever and OpenAI's vision* 00:15:51 Leaving OpenAI to start Dust* 00:18:15 Early focus on browser extension and WebGPT-like functionality* 00:20:20 Dust as the infrastructure for agents* 00:24:03 Challenges of building with early AI models* 00:28:17 LLMs and Workflow Automation* 00:35:28 Building dependency graphs of agents* 00:37:34 Simulating API endpoints* 00:40:41 State of AI models* 00:43:19 Running evals* 00:46:36 Challenges in building AI agents infra* 00:49:21 Buy vs. build decisions for infrastructure components* 00:51:02 Future of SaaS and AI's Impact on Software* 00:53:07 The single employee $1B company race* 00:56:32 Horizontal vs. vertical approaches to AI agentsTranscriptAlessio [00:00:00]: Hey everyone, welcome to the Latent Space podcast. This is Alessio, partner and CTO at Decibel Partners, and I'm joined by my co-host Swyx, founder of Smol.ai.Swyx [00:00:11]: Hey, and today we're in a studio with Stanislas, welcome.Stan [00:00:14]: Thank you very much for having me.Swyx [00:00:16]: Visiting from Paris.Stan [00:00:17]: Paris.Swyx [00:00:18]: And you have had a very distinguished career. It's very hard to summarize, but you went to college in both Ecopolytechnique and Stanford, and then you worked in a number of places, Oracle, Totems, Stripe, and then OpenAI pre-ChatGPT. We'll talk, we'll spend a little bit of time about that. About two years ago, you left OpenAI to start Dust. I think you were one of the first OpenAI alum founders.Stan [00:00:40]: Yeah, I think it was about at the same time as the Adept guys, so that first wave.Swyx [00:00:46]: Yeah, and people really loved our David episode. We love a few sort of OpenAI stories, you know, for back in the day, like we're talking about pre-recording. Probably the statute of limitations on some of those stories has expired, so you can talk a little bit more freely without them coming after you. But maybe we'll just talk about, like, what was your journey into AI? You know, you were at Stripe for almost five years, there are a lot of Stripe alums going into OpenAI. I think the Stripe culture has come into OpenAI quite a bit.Stan [00:01:11]: Yeah, so I think the buses of Stripe people really started flowing in, I guess, after ChatGPT. But, yeah, my journey into AI is a... I mean, Greg Brockman. Yeah, yeah. From Greg, of course. And Daniela, actually, back in the days, Daniela Amodei.Swyx [00:01:27]: Yes, she was COO, I mean, she is COO, yeah. She had a pretty high job at OpenAI at the time, yeah, for sure.Stan [00:01:34]: My journey started as anybody else, you're fascinated with computer science and you want to make them think, it's awesome, but it doesn't work. I mean, it was a long time ago, it was like maybe 16, so it was 25 years ago. Then the first big exposure to AI would be at Stanford, and I'm going to, like, disclose a whole lamb, because at the time it was a class taught by Andrew Ng, and there was no deep learning. It was half features for vision and a star algorithm. So it was fun. But it was the early days of deep learning. At the time, I think a few years after, it was the first project at Google. But you know, that cat face or the human face trained from many images. I went to, hesitated doing a PhD, more in systems, eventually decided to go into getting a job. Went at Oracle, started a company, did a gazillion mistakes, got acquired by Stripe, worked with Greg Buckman there. And at the end of Stripe, I started interesting myself in AI again, felt like it was the time, you had the Atari games, you had the self-driving craziness at the time. And I started exploring projects, it felt like the Atari games were incredible, but there were still games. And I was looking into exploring projects that would have an impact on the world. And so I decided to explore three things, self-driving cars, cybersecurity and AI, and math and AI. It's like I sing it by a decreasing order of impact on the world, I guess.Swyx [00:03:01]: Discovering new math would be very foundational.Stan [00:03:03]: It is extremely foundational, but it's not as direct as driving people around.Swyx [00:03:07]: Sorry, you're doing this at Stripe, you're like thinking about your next move.Stan [00:03:09]: No, it was at Stripe, kind of a bit of time where I started exploring. I did a bunch of work with friends on trying to get RC cars to drive autonomously. Almost started a company in France or Europe about self-driving trucks. We decided to not go for it because it was probably very operational. And I think the idea of the company, of the team wasn't there. And also I realized that if I wake up a day and because of a bug I wrote, I killed a family, it would be a bad experience. And so I just decided like, no, that's just too crazy. And then I explored cybersecurity with a friend. We're trying to apply transformers to cut fuzzing. So cut fuzzing, you have kind of an algorithm that goes really fast and tries to mutate the inputs of a library to find bugs. And we tried to apply a transformer to that and do reinforcement learning with
Apologies for lower audio quality; we lost recordings and had to use backup tracks. Our guests today are Anastasios Angelopoulos and Wei-Lin Chiang, leads of Chatbot Arena, fka LMSYS, the crowdsourced AI evaluation platform developed by the LMSys student club at Berkeley, which became the de facto standard for comparing language models. Arena Elo is often more cited than MMLU scores to many folks, and they have attracted >1,000,000 people to cast votes since its launch, leading top model trainers to cite them over their own formal academic benchmarks:The Limits of Static BenchmarksWe’ve done two benchmarks episodes: Benchmarks 101 and Benchmarks 201. One issue we’ve always brought up with static benchmarks is that 1) many are getting saturated, with models scoring almost perfectly on them 2) they often don’t reflect production use cases, making it hard for developers and users to use them as guidance. The fundamental challenge in AI evaluation isn't technical - it's philosophical. How do you measure something that increasingly resembles human intelligence? Rather than trying to define intelligence upfront, Arena let users interact naturally with models and collect comparative feedback. It's messy and subjective, but that's precisely the point - it captures the full spectrum of what people actually care about when using AI.The Pareto Frontier of Cost vs IntelligenceBecause the Elo scores are remarkably stable over time, we can put all the chat models on a map against their respective cost to gain a view of at least 3 orders of magnitude of model sizes/costs and observe the remarkable shift in intelligence per dollar over the past year:This frontier stood remarkably firm through the recent releases of o1-preview and price cuts of Gemini 1.5:The Statistics of SubjectivityIn our Benchmarks 201 episode, Clémentine Fourrier from HuggingFace thought this design choice was one of shortcomings of arenas: they aren’t reproducible. You don’t know who ranked what and what exactly the outcome was at the time of ranking. That same person might rank the same pair of outputs differently on a different day, or might ask harder questions to better models compared to smaller ones, making it imbalanced. Another argument that people have brought up is confirmation bias. We know humans prefer longer responses and are swayed by formatting - Rob Mulla from Dreadnode had found some interesting data on this in May:The approach LMArena is taking is to use logistic regression to decompose human preferences into constituent factors. As Anastasios explains: "We can say what components of style contribute to human preference and how they contribute." By adding these style components as parameters, they can mathematically "suck out" their influence and isolate the core model capabilities.This extends beyond just style - they can control for any measurable factor: "What if I want to look at the cost adjusted performance? Parameter count? We can ex post facto measure that." This is one of the most interesting things about Arena: You have a data generation engine which you can clean and turn into leaderboards later. If you wanted to create a leaderboard for poetry writing, you could get existing data from Arena, normalize it by identifying these style components. Whether or not it’s possible to really understand WHAT bias the voters have, that’s a different question.Private EvalsOne of the most delicate challenges LMSYS faces is maintaining trust while collaborating with AI labs. The concern is that labs could game the system by testing multiple variants privately and only releasing the best performer. This was brought up when 4o-mini released and it ranked as the second best model on the leaderboard:But this fear misunderstands how Arena works. Unlike static benchmarks where selection bias is a major issue, Arena's live nature means any initial bias gets washed out by ongoing evaluation. As Anastasios explains: "In the long run, there's way more fresh data than there is data that was used to compare these five models." The other big question is WHAT model is actually being tested; as people often talk about on X / Discord, the same endpoint will randomly feel “nerfed” like it happened for “Claude European summer” and corresponding conspiracy theories:It’s hard to keep track of these performance changes in Arena as these changes (if real…?) are not observable.The Future of EvaluationThe team's latest work on RouteLLM points to an interesting future where evaluation becomes more granular and task-specific. But they maintain that even simple routing strategies can be powerful - like directing complex queries to larger models while handling simple tasks with smaller ones.Arena is now going to expand beyond text into multimodal evaluation and specialized domains like code execution and red teaming. But their core insight remains: the best way to evaluate intelligence isn't to simplify it into metrics, but to embrace its complexity and find rigorous ways to analyze it. To go after this vision, they are spinning out Arena from LMSys, which will stay as an academia-driven group at Berkeley.Full Video PodcastChapters* 00:00:00 - Introductions* 00:01:16 - Origin and development of Chatbot Arena* 00:05:41 - Static benchmarks vs. Arenas* 00:09:03 - Community building* 00:13:32 - Biases in human preference evaluation* 00:18:27 - Style Control and Model Categories* 00:26:06 - Impact of o1* 00:29:15 - Collaborating with AI labs* 00:34:51 - RouteLLM and router models* 00:38:09 - Future of LMSys / ArenaShow Notes* Anastasios Angelopoulos* Anastasios' NeurIPS Paper Conformal Risk Control* Wei-Lin Chiang* Chatbot Arena* LMSys* MTBench* ShareGPT dataset* Stanford's Alpaca project* LLMRouter* E2B* DreadnodeTranscriptAlessio [00:00:00]: Hey everyone, welcome to the Latent Space podcast. This is Alessio, Partner and CTO in Residence at Decibel Partners, and I'm joined by my co-host Swyx, founder of Smol.ai.Swyx [00:00:14]: Hey, and today we're very happy and excited to welcome Anastasios and Wei Lin from LMSys. Welcome guys.Wei Lin [00:00:21]: Hey, how's it going? Nice to see you.Anastasios [00:00:23]: Thanks for having us.Swyx [00:00:24]: Anastasios, I actually saw you, I think at last year's NeurIPS. You were presenting a paper, which I don't really super understand, but it was some theory paper about how your method was very dominating over other sort of search methods. I don't remember what it was, but I remember that you were a very confident speaker.Anastasios [00:00:40]: Oh, I totally remember you. Didn't ever connect that, but yes, that's definitely true. Yeah. Nice to see you again.Swyx [00:00:46]: Yeah. I was frantically looking for the name of your paper and I couldn't find it. Basically I had to cut it because I didn't understand it.Anastasios [00:00:51]: Is this conformal PID control or was this the online control?Wei Lin [00:00:55]: Blast from the past, man.Swyx [00:00:57]: Blast from the past. It's always interesting how NeurIPS and all these academic conferences are sort of six months behind what people are actually doing, but conformal risk control, I would recommend people check it out. I have the recording. I just never published it just because I was like, I don't understand this enough to explain it.Anastasios [00:01:14]: People won't be interested.Wei Lin [00:01:15]: It's all good.Swyx [00:01:16]: But ELO scores, ELO scores are very easy to understand. You guys are responsible for the biggest revolution in language model benchmarking in the last few years. Maybe you guys want to introduce yourselves and maybe tell a little bit of the brief history of LMSysWei Lin [00:01:32]: Hey, I'm Wei Lin. I'm a fifth year PhD student at UC Berkeley, working on Chatbot Arena these days, doing crowdsourcing AI benchmarking.Anastasios [00:01:43]: I'm Anastasios. I'm a sixth year PhD student here at Berkeley. I did most of my PhD on like theoretical statistics and sort of foundations of model evaluation and testing. And now I'm working 150% on this Chatbot Arena stuff. It's great.Alessio [00:02:00]: And what was the origin of it? How did you come up with the idea? How did you get people to buy in? And then maybe what were one or two of the pivotal moments early on that kind of made it the standard for these things?Wei Lin [00:02:12]: Yeah, yeah. Chatbot Arena project was started last year in April, May, around that. Before that, we were basically experimenting in a lab how to fine tune a chatbot open source based on the Llama 1 model that I released. At that time, Lama 1 was like a base model and people didn't really know how to fine tune it. So we were doing some explorations. We were inspired by Stanford's Alpaca project. So we basically, yeah, grow a data set from the internet, which is called ShareGPT data set, which is like a dialogue data set between user and chat GPT conversation. It turns out to be like pretty high quality data, dialogue data. So we fine tune on it and then we train it and release the model called V2. And people were very excited about it because it kind of like demonstrate open way model can reach this conversation capability similar to chat GPT. And then we basically release the model with and also build a demo website for the model. People were very excited about it. But during the development, the biggest challenge to us at the time was like, how do we even evaluate it? How do we even argue this model we trained is better than others? And then what's the gap between this open source model that other proprietary offering? At that time, it was like GPT-4 was just announced and it's like Cloud One. What's the difference between them? And then after that, like every week, there's a new model being fine tuned, released. So even until still now, right? And then we have that demo website for V2 now. And then we thought like, okay, maybe we can add a few more of the model as well, like API model as well. And then we quickly realized that
If you’ve listened to the podcast for a while, you might have heard our ElevenLabs-powered AI co-host Charlie a few times. Text-to-speech has made amazing progress in the last 18 months, with OpenAI’s Advanced Voice Mode (aka “Her”) as a sneak peek of the future of AI interactions (see our “Building AGI in Real Time” recap). Yet, we had yet to see a real killer app for AI voice (not counting music).Today’s guests, Raiza Martin and Usama Bin Shafqat, are the lead PM and AI engineer behind the NotebookLM feature flag that gave us the first viral AI voice experience, the “Deep Dive” podcast:The idea behind the “Audio Overviews” feature is simple: take a bunch of documents, websites, YouTube videos, etc, and generate a podcast out of them. This was one of the first demos that people built with voice models + RAG + GPT models, but it was always a glorified speech-to-text. Raiza and Usama took a very different approach:* Make it conversational: when you listen to a NotebookLM audio there are a ton of micro-interjections (Steven Johnson calls them disfluencies) like “Oh really?” or “Totally”, as well as pauses and “uh…”, like you would expect in a real conversation. These are not generated by the LLM in the transcript, but they are built into the the audio model. See ~28:00 in the pod for more details. * Listeners love tension: if two people are always in agreement on everything, it’s not super interesting. They tuned the model to generate flowing conversations that mirror the tone and rhythm of human speech. They did not confirm this, but many suspect the 2 year old SoundStorm paper is related to this model.* Generating new insights: because the hosts’ goal is not to summarize, but to entertain, it comes up with funny metaphors and comparisons that actually help expand on the content rather than just paraphrasing like most models do. We have had listeners make podcasts out of our podcasts, like this one.This is different than your average SOTA-chasing, MMLU-driven model buildooor. Putting product and AI engineering in the same room, having them build evals together, and understanding what the goal is lets you get these unique results. The 5 rules for AI PMsWe always focus on AI Engineers, but this episode had a ton of AI PM nuggets as well, which we wanted to collect as NotebookLM is one of the most successful products in the AI space:1. Less is more: the first version of the product had 0 customization options. All you could do is give it source documents, and then press a button to generate. Most users don’t know what “temperature” or “top-k” are, so you’re often taking the magic away by adding more options in the UI. Since recording they added a few, like a system prompt, but those were features that users were “hacking in”, as Simon Willison highlighted in his blog post.2. Use Real-Time Feedback: they built a community of 65,000 users on Discord that is constantly reporting issues and giving feedback; sometimes they noticed server downtime even before the Google internal monitoring did. Getting real time pings > aggregating user data when doing initial iterations. 3. Embrace Non-Determinism: AI outputs variability is a feature, not a bug. Rather than limiting the outputs from the get-go, build toggles that you can turn on/off with feature flags as the feedback starts to roll in.4. Curate with Taste: if you try your product and it sucks, you don’t need more data to confirm it. Just scrap that and iterate again. This is even easier for a product like this; if you start listening to one of the podcasts and turn it off after 10 seconds, it’s never a good sign. 5. Stay Hands-On: It’s hard to build taste if you don’t experiment. Trying out all your competitors products as well as unrelated tools really helps you understand what users are seeing in market, and how to improve on it.Chapters00:00 Introductions01:39 From Project Tailwind to NotebookLM09:25 Learning from 65,000 Discord members12:15 How NotebookLM works18:00 Working with Steven Johnson23:00 How to prioritize features25:13 Structuring the data pipelines29:50 How to eval34:34 Steering the podcast outputs37:51 Defining speakers personalities39:04 How do you make audio engaging?45:47 Humor is AGI51:38 Designing for non-determinism53:35 API when?55:05 Multilingual support and dialect considerations57:50 Managing system prompts and feature requests01:00:58 Future of NotebookLM01:04:59 Podcasts for your codebase01:07:16 Plans for real-time chat01:08:27 Wrap upShow Notes* Notebook LM* AI Test Kitchen* Nicholas Carlini* Steven Johnson* Wealth of Nations* Histories of Mysteries by Andrej Karpathy* chicken.pdf Threads* Area 120* Raiza Martin* Usama Bin ShafqatTranscriptNotebookLM [00:00:00]: Hey everyone, we're here today as guests on Latent Space. It's great to be here, I'm a long time listener and fan, they've had some great guests on this show before. Yeah, what an honor to have us, the hosts of another podcast, join as guests. I mean a huge thank you to Swyx and Alessio for the invite, thanks for having us on the show. Yeah really, it seems like they brought us here to talk a little bit about our show, our podcast. Yeah, I mean we've had lots of listeners ourselves, listeners at Deep Dive. Oh yeah, we've made a ton of audio overviews since we launched and we're learning a lot. There's probably a lot we can share around what we're building next, huh? Yeah, we'll share a little bit at least. The short version is we'll keep learning and getting better for you. We're glad you're along for the ride. So yeah, keep listening. Keep listening and stay curious. We promise to keep diving deep and bringing you even better options in the future. Stay curious.Alessio [00:00:52]: Hey everyone, welcome to the Latent Space Podcast. This is Alessio, partner and CTO at Residence at Decibel Partners. And I'm joined by my co-host, Swyx, founder of Smol.ai.Swyx [00:01:01]: Hey, and today we're back in the studio with our special guest, Raiza Martin. And Raiza, I forgot to get your last name, Shafqat.Raiza [00:01:10]: Yes.Swyx [00:01:10]: Okay, welcome.Raiza [00:01:12]: Hello, thank you for having us.Swyx [00:01:14]: So AI podcasters meet human podcasters, always fun. Congrats on the success of Notebook LM. I mean, how does it feel?Raiza [00:01:22]: It's been a lot of fun. A lot of it, honestly, was unexpected. But my favorite part is really listening to the audio overviews that people have been making.Swyx [00:01:29]: Maybe we should do a little bit of intros and tell the story. You know, what is your path into the sort of Google AI org? Or maybe, actually, I don't even know what org you guys are in.Raiza [00:01:39]: I can start. My name is Raisa. I lead the Notebook LM team inside of Google Labs. So specifically, that's the org that we're in. It's called Google Labs. It's only about two years old. And our whole mandate is really to build AI products. That's it. We work super closely with DeepMind. Our entire thing is just, like, try a bunch of things and see what's landing with users. And the background that I have is, really, I worked in payments before this, and I worked in ads right before, and then startups. I tell people, like, at every time that I changed orgs, I actually almost quit Google. Like, specifically, like, in between ads and payments, I was like, all right, I can't do this. Like, this is, like, super hard. I was like, it's not for me. I'm, like, a very zero-to-one person. But then I was like, okay, I'll try. I'll interview with other teams. And when I interviewed in payments, I was like, oh, these people are really cool. I don't know if I'm, like, a super good fit with this space, but I'll try it because the people are cool. And then I really enjoyed that, and then I worked on, like, zero-to-one features inside of payments, and I had a lot of fun. But then the time came again where I was like, oh, I don't know. It's like, it's time to leave. It's time to start my own thing. But then I interviewed inside of Google Labs, and I was like, oh, darn. Like, there's definitely, like—Alessio [00:02:48]: They got you again.Raiza [00:02:49]: They got me again. And so now I've been here for two years, and I'm happy that I stayed because especially with, you know, the recent success of Notebook LM, I'm like, dang, we did it. I actually got to do it. So that was really cool.Usama [00:03:02]: Kind of similar, honestly. I was at a big team at Google. We do sort of the data center supply chain planning stuff. Google has, like, the largest sort of footprint. Obviously, there's a lot of management stuff to do there. But then there was this thing called Area 120 at Google, which does not exist anymore. But I sort of wanted to do, like, more zero-to-one building and landed a role there. We were trying to build, like, a creator commerce platform called Kaya. It launched briefly a couple years ago. But then Area 120 sort of transitioned and morphed into Labs. And, like, over the last few years, like, the focus just got a lot clearer. Like, we were trying to build new AI products and do it in the wild and sort of co-create and all of that. So, you know, we've just been trying a bunch of different things. And this one really landed, which has felt pretty phenomenal. Really, really landed.Swyx [00:03:53]: Let's talk about the brief history of Notebook LM. You had a tweet, which is very helpful for doing research. May 2023, during Google I.O., you announced Project Tailwind.Raiza [00:04:03]: Yeah.Swyx [00:04:03]: So today is October 2024. So you joined October 2022?Raiza [00:04:09]: Actually, I used to lead AI Test Kitchen. And this was actually, I think, not I.O. 2023. I.O. 2022 is when we launched AI Test Kitchen, or announced it. And I don't know if you remember it.Swyx [00:04:23]: That's how you, like, had the basic prototype for Gemini.Raiza [00:04:26]: Yes, yes, exactly. Lambda.Swyx [00:04:28]: Gave beta access to people.Raiza [00:04:29]: Yeah, yeah, yeah. And I remember, I was like, wo
Singapore's GovTech is hosting an AI CTF challenge with ~$15,000 in prizes, starting October 26th, open to both local and virtual hackers. It will be hosted on Dreadnode's Crucible platform; signup here!It is common to say if you want to work in AI, you should come to San Francisco. Not everyone can. Not everyone should. If you can only do meaningful AI work in one city, then AI has failed to generalize meaningfully.As non-Americans working in the US, we know what it’s like to see AI progress so rapidly here, and yet be at a loss for what our home countries can do. Through Latent Space we’ve tried to tell the story of AI outside of the Bay Area bubble; we talked to Notion in New York and Humanloop and Wondercraft in London and HuggingFace in Paris and ICLR in Vienna, and the Reka, RWKV, and Winds of AI Winter episodes were taped in Singapore (the World’s Fair also had Latin America representation and we intend to at least add China, Japan, and India next year).The Role of Government with AIAs an intentionally technical resource, we’ve mostly steered clear of regulation and safety debates on the podcast; whether it is safety bills or technoalarmism, often at the cost of our engagement numbers or ability to book big name guests with a political agenda. When SOTA shifts 3x faster than it takes to pass a law, when nobody agrees on definitions of important things, when you can elicit never-before-seen behavior by slightly different prompting or sampling, it is hard enough to simply keep up to speed, so we are happy limiting our role to that. The story of AI progress has more often been achieved in the private sector, usually in spite of, rather than with thanks to, government intervention.But industrial policy is inextricably linked to the business of AI, which we do very much care about, has an explicitly accelerationist intent if not impact, and has a track record of success in correcting for legitimate market failures in private sector investment, particularly outside of the US. It is with this lens we approach today’s episode and special guest, our first with a sitting Cabinet member.Singapore’s National AI StrategyIt is well understood that much of Singapore’s economic success is attributable to industrial policy, from direct efforts like the Jurong Town Corporation industrialization to indirect ones like going all in on English as national first language. Singapore’s National AI Strategy grew out of its 2014 Smart Nation initiative, first launched in 2019 and then refreshed in 2023 by Minister Josephine Teo, our guest today.While Singapore is not often thought of as an AI leader, the National University ranks in the top 10 in publications (above Oxford/Harvard!), and many overseas Singaporeans work at the leading AI companies and institutions in the US (and some of us even run leading AI Substacks?). OpenAI has often publicly named the Singapore government as their model example of government collaborator and is opening an office in Singapore in time for DevDay 2024.AI Engineer NationsSwyx first pitched the AI Engineer Nation concept at a private Sovereign AI summit featuring Dr. He Ruimin, Chief AI Officer of Singapore, which eventually led to an invitation to discuss the concept with Minister Teo, the country’s de-facto minister for tech (she calls it Digital Development, for good reasons she explains in the pod).This chat happened (with thanks to Jing Long, Joyce, and other folks from MDDI)!The central pitch for any country, not just Singapore, to emphasize and concentrate bets on AI Engineers, compared with other valuable efforts like training more researchers, releasing more government-approved data, or offering more AI funding, is a calculated one, based on the fact that: * GPU clusters and researchers have massive returns to scale and colocation, mostly concentrated in the US, that are irresponsibly expensive to replicate* Even if research stopped today and there was no progress for the next 30 years, there are far more capabilities to unlock and productize from existing foundation models and we <5% done on this journey* Good AI Engineering requires genuine skill and is deepening enough to justify sub-specialization as a sub-industry of Software Engineering* Companies and countries with better AI engineer workforces will disproportionately benefit from AI vs those who equivocate it as one of many equivalent priorities* Tech progress is often framed as “the future is here but it is not evenly distributed”. The role of the AI Engineer is therefore to better distribute the state of the art to as much of humanity as possible, including the elderly, poor, and differently abled.All of which are themes we first identified in the Rise of the AI Engineer. Singapore simply has a few additional factors that make it not just a good fit, but an economic imperative:* English speaking, very-online country that is great at STEM* Aging, ex-growth population (Total Fertility Rate of 1.1)* #3 GDP per capita (PPP) country in the world* Physically remote from major economic growth centers ex China/SEAThat basically dictates that any continued economic growth must be disconnected to geography, timezone, or headcount, or reliance on existing industrial drivers. Short of holding Taylor Swift hostage, making an intentional, concentrated bet on AI industrial policy is Singapore’s best option to keep up progress in the 21st century. As a pioneer in education policy being the primary long term determinant of economic success, this may result in Python as Singapore’s next National Language in the long run, a proposal we also discussed extensively at the RAISE retreat where this episode was recorded.Because of upcoming election season concerns around the globe, we also took the opportunity to ask about Singapore’s recent deepfake (election integrity) law.Full YouTube episodeShow Notes* Josephine Teo Official Bio, Wikipedia* Singapore National AI Strategy* 2019 - v1* 2023 - v2* ICLR (machine learning conference)* Philipp Kandal (CPO of Grab)* Temasek* GIC* EDBI* Economic Development Board (EDB)* Michael Fay incident* Quincy Larson* AIBots (internal RAG system for Singapore government)* Slovakia election incident* National AI Strategy - Singapore* Singapore AI Safety Institute* AI Verify* SkillsFuture* Ministry of Digital Development and Information (MDDI)* GovTech* NTU (Nanyang Technological University)Timestamps00:00:00 Introductions00:00:34 Singapore's National AI Strategy00:02:50 Ministry of Digital Development and Information00:08:49 Defining a National AI Strategy00:14:32 AI Safety and Governance00:16:50 AI Adoption in Companies and Government00:19:53 Balancing AI Innovation and Safety00:22:56 Structuring Government for Rapid Technological Change00:27:08 Doing Business with Singapore00:32:21 Training and Workforce Development in AI00:37:05 Career Transition Help for Post-AI Jobs00:40:19 AI Literacy and Coding as a Language00:43:28 Sovereign AI and Digital Infrastructure00:50:48 Government and AI Workloads00:51:02 Favorite AI Use Case in Government00:53:52 AI and ElectionsTranscriptAlessio [00:00:00]: Hey everyone, welcome to the Latent Space podcast. This is Alessio, partner and CTO at Residence at Decibel Partners, and I'm joined by my co-host Swyx, founder of Small.ai.Swyx [00:00:13]: Hey everyone, this is a very, very special episode. We have here Mr. Josephine Teo from Singapore. Welcome.Josephine [00:00:19]: Hi Shawn and hi Alessio. Thank you for having me. Of course.Swyx [00:00:23]: You are the Minister for Digital Development and Information and Second Minister for Home Affairs. We're meeting here at RAISE, which is effectively your agency. Maybe we want to explain a little bit about what Singapore is doing in AI.Josephine [00:00:34]: Well, we've had an AI strategy at the national level for some years now, and about two years ago when generative AI became so prominent, we thought it was about time for us to refresh our national AI strategy. And it's not unusual on such occasions for us to consult widely. We want to talk to people who are familiar with the field. We want to talk to people who are active as practitioners, and we also want to talk to people in Singapore who have an interest in seeing the AI ecosystem develop. So when we put all these together, we discovered something else by chance, and it was really a bonus. This was the fact that there were already Singaporeans that were active in the AI space, particularly in the US, particularly in the Bay Area. And one of the exciting things for us was how could we also consult these Singaporeans who clearly still have a passion for Singapore, they do care about what happens back home, and they want to contribute to it. So that's how RAISE came about. And RAISE actually preceded the publication of the refresh of our national AI strategy, which took place in December last year. So the inputs of the participants from RAISE helped us to sharpen what we thought would be important in building up the AI ecosystem. And also with the encouragement of participants at RAISE, primarily Singaporeans who were doing great work in the US, we decided to raise our ambitions, literally. That's why we say AI for the public good, recognising the fact that commercial interest will certainly drive exciting developments in the industry space. But keep in mind, there is a need to make sure that AI serves the public good. And we say for Singapore and the world. So the idea is that experiments that are carried out in Singapore, things that are scaled up in Singapore potentially could have contributions elsewhere in the world. And so AI for the public good, for Singapore and the world. That's how it came about.Alessio [00:02:50]: I was listening to some of your previous interviews, and even the choice of the name development in the ministry name was very specific. You mentioned naming is your ethos. Can you explain maybe a bit about what the ministry does, which is not simply funding R&D, but i
CEOs of publicly traded companies are often in the news talking about their new AI initiatives, but few of them have built anything with it. Drew Houston from Dropbox is different; he has spent over 400 hours coding with LLMs in the last year and is now refocusing his 2,500+ employees around this new way of working, 17 years after founding the company.Timestamps00:00 Introductions00:43 Drew's AI journey04:14 Revalidating expectations of AI08:23 Simulation in self-driving vs. knowledge work12:14 Drew's AI Engineering setup15:24 RAG vs. long context in AI models18:06 From "FileGPT" to Dropbox AI23:20 Is storage solved?26:30 Products vs Features30:48 Building trust for data access33:42 Dropbox Dash and universal search38:05 The evolution of Dropbox42:39 Building a "silicon brain" for knowledge work48:45 Open source AI and its impact51:30 "Rent, Don't Buy" for AI54:50 Staying relevant58:57 Founder Mode01:03:10 Advice for founders navigating AI01:07:36 Building and managing teams in a growing companyTranscriptAlessio [00:00:00]: Hey everyone, welcome to the Latent Space podcast. This is Alessio, partner and CTO at Decibel Partners, and there's no Swyx today, but I'm joined by Drew Houston of Dropbox. Welcome, Drew.Drew [00:00:14]: Thanks for having me.Alessio [00:00:15]: So we're not going to talk about the Dropbox story. We're not going to talk about the Chinatown bus and the flash drive and all that. I think you've talked enough about it. Where I want to start is you as an AI engineer. So as you know, most of our audience is engineering folks, kind of like technology leaders. You obviously run Dropbox, which is a huge company, but you also do a lot of coding. I think that's how you spend almost 400 hours, just like coding. So let's start there. What was the first interaction you had with an LLM API and when did the journey start for you?Drew [00:00:43]: Yeah. Well, I think probably all AI engineers or whatever you call an AI engineer, those people started out as engineers before that. So engineering is my first love. I mean, I grew up as a little kid. I was that kid. My first line of code was at five years old. I just really loved, I wanted to make computer games, like this whole path. That also led me into startups and eventually starting Dropbox. And then with AI specifically, I studied computer science, I got my, I did my undergrad, but I didn't do like grad level computer science. I didn't, I sort of got distracted by all the startup things, so I didn't do grad level work. But about several years ago, I made a couple of things. So one is I sort of, I knew I wanted to go from being an engineer to a founder. And then, but sort of the becoming a CEO part was sort of backed into the job. And so a couple of realizations. One is that, I mean, there's a lot of like repetitive and like manual work you have to do as an executive that is actually lends itself pretty well to automation, both for like my own convenience. And then out of interest in learning, I guess what we call like classical machine learning these days, I started really trying to wrap my head around understanding machine learning and informational retrieval more, more formally. So I'd say maybe 2016, 2017 started me writing these more successively, more elaborate scripts to like understand basic like classifiers and regression and, and again, like basic information retrieval and NLP back in those days. And there's sort of like two things that came out of that. One is techniques are super powerful. And even just like studying like old school machine learning was a pretty big inversion of the way I had learned engineering, right? You know, I started programming when everyone starts programming and you're, you're sort of the human, you're giving an algorithm to the, and spelling out to the computer how it should run it. And then machine learning, here's machine learning where it's like actually flip that, like give it sort of the answer you want and it'll figure out the algorithm, which was pretty mind bending. And it was both like pretty powerful when I would write tools, like figure out like time audits or like, where's my time going? Is this meeting a one-on-one or is it a recruiting thing or is it a product strategy thing? I started out doing that manually with my assistant, but then found that this was like a very like automatable task. And so, which also had the side effect of teaching me a lot about machine learning. But then there was this big problem, like anytime you, it was very good at like tabular structured data, but like anytime it hit, you know, the usual malformed English that humans speak, it would just like fall over. I had to kind of abandon a lot of the things that I wanted to build because like there's no way to like parse text. Like maybe it would sort of identify the part of speech in a sentence or something. But then fast forward to the LLM, I mean actually I started trying some of like this, what we would call like very small LLMs before kind of the GPT class models. And it was like super hard to get those things working. So like these 500 parameter models would just be like hallucinating and repeating and you know. So actually I'd kind of like written it off a little bit. But then the chat GPT launch and GPT-3 for sure. And then once people figured out like prompting and instruction tuning, this was sort of like November-ish 2022 like everybody else sort of that the chat GPT launch being the starting gun for the whole AI era of computing and then having API access to three and then early access to GPT-4. I was like, oh man, it's happening. And so I was literally on my honeymoon and we're like on a beach in Thailand and I'm like coding these like AI tools to automate like writing or to assist with writing and all these different use cases.Alessio [00:04:14]: You're like, I'm never going back to work. I'm going to automate all of it before I get back.Drew [00:04:17]: And I was just, you know, ever since then, I mean, I've always been like coding like prototypes and just stuff to make my life more convenient, but like escalated a lot after 22. And yeah, I spent, I checked, I think it was probably like over 400 hours this year so far coding because I had my paternity leave where I was able to work on some special projects. But yeah, it's a super important part of like my whole learning journey is like being really hands-on with these things. And I mean, it's probably not a typical recipe, but I really love to get down to the metal as far as how this stuff works.Alessio [00:04:47]: Yeah. So Swyx and I were with Sam Altman in October 22. We were like at a hack day at OpenAI and that's why we started this podcast eventually. But you did an interview with Sam like seven years ago and he asked you what's the biggest opportunity in startups and you were like machine learning and AI and you were almost like too early, right? It's like maybe seven years ago, the models weren't quite there. How should people think about revalidating like expectations of this technology? You know, I think even today people will tell you, oh, models are not really good at X because they were not good 12 months ago, but they're good today.Drew [00:05:19]: What's your project? Heuristics for thinking about that or how is, yeah, I think the way I look at it now is pretty, has evolved a lot since when I started. I mean, I think everybody intuitively starts with like, all right, let's try to predict the future or imagine like what's this great end state we're going to get to. And the tricky thing is like often those prognostications are right, but they're right in terms of direction, but not when. For example, you know, even in the early days of the internet, 90s when things were even like tech space and you know, even before like the browser or things like that, people were like, oh man, you're going to have, you know, you're going to be able to order food, get like a Snickers delivered to your house, you're going to be able to watch any movie ever created. And they were right. But they were like, you know, it took 20 years for that to actually happen. And before you got to DoorDash, you had to get, you started with like Webvan and Cosmo and before you get to Spotify, you had to do like Napster and Kazaa and LimeWire and like a bunch of like broken Britney Spears MP3s and malware. So I think the big lesson is being early is the same as being wrong. Being late is the same as being wrong. So really how do you calibrate timing? And then I think with AI, it's the same thing that people are like, oh, it's going to completely upend society and all these positive and negative ways. I think that's like most of those things are going to come true. The question is like, when is that going to happen? And then with AI specifically, I think there's also, in addition to sort of the general tech category or like jumping too fast to the future, I think that AI is particularly susceptible to that. And you look at self-driving, right? This idea of like, oh my God, you can have a self-driving car captured everybody's imaginations 10, 12 years ago. And you know, people are like, oh man, in two years, there's not going to be another year. There's not going to be a human driver on the road to be seen. It didn't work out that way, right? We're still 10, 12 years later where we're in a world where you can sort of sometimes get a Waymo in like one city on earth. Exciting, but just took a lot longer than people think. And the reason is there's a lot of engineering challenges, but then there's a lot of other like societal time constants that are hard to compress. So one thing I think you can learn from things like self-driving is they have these levels of autonomy that's a useful kind of framework in driving or these like maturity levels. People sort of skip to like level five, full autonomy, or we're going to have like an autonomous knowledge worker that's just going to take, that's going
We are in 🗽 NYC this Monday! Join the AI Eng NYC meetup, bring demos and vibes!It is a bit of a meme that the first thing developer tooling founders think to build in AI is all the non-AI operational stuff outside the AI. There are well over 60 funded LLM Ops startups all with hoping to solve the new observability, cost tracking, security, and reliability problems that come with putting LLMs in production, not to mention new LLM oriented products from incumbent, established ops/o11y players like Datadog and Weights & Biases. 2 years in to the current hype cycle, the early winners have tended to be people with practical/research AI backgrounds rather than MLOps heavyweights or SWE tourists:* LangSmith: We covered how Harrison Chase worked on AI at Robust Intelligence and Kensho, the alma maters of many great AI founders* HumanLoop: We covered how Raza Habib worked at Google AI during his PhD* BrainTrust: Today’s guest Ankur Goyal founded Impira pre-Transformers and was acquihired to run Figma AI before realizing how to solve the Ops problem.There have been many VC think pieces and market maps describing what people thought were the essential pieces of the AI Engineering stack, but what was true for 2022-2023 has aged poorly. The basic insight that Ankur had is the same thesis that Hamel Husain is pushing in his World’s Fair talk and podcast with Raza and swyx:Evals are the centerpiece of systematic AI Engineering.REALLY believing in this is harder than it looks with the benefit of hindsight. It’s not like people didn’t know evals were important. Basically every LLM Ops feature list has them. It’s an obvious next step AFTER managing your prompts and logging your LLM calls. In fact, up til we met Braintrust, we were working on an expanded version of the Impossible Triangle Theory of the LLM Ops War that we first articulated in the Humanloop writeup:The single biggest criticism of the Rise of the AI Engineer piece is that we neglected to split out the role of product evals (as opposed to model evals) in the now infamous “API line” chart:With hindsight, we were very focused on the differentiating 0 to 1 phase that AI Engineers can bring to an existing team of ML engineers. As swyx says on the Day 2 keynote of AI Engineer, 2024 added a whole new set of concerns as AI Engineering grew up:A closer examination of Hamel’s product-oriented virtuous cycle and this infra-oriented SDLC would have eventually revealed that Evals, even more than logging, was the first point where teams start to get really serious about shipping to production, and therefore a great place to make an entry into the marketplace, which is exactly what Braintrust did.Also notice what’s NOT on this chart: shifting to shadow open source models, and finetuning them… per Ankur, Fine-tuning is not a viable standalone product:“The thing I would say is not debatable is whether or not fine-tuning is a business outcome or not. So let's think about the other components of your triangle. Ops/observability, that is a business… Frameworks, evals, databases [are a business, but] Fine-tuning is a very compelling method that achieves an outcome. The outcome is not fine-tuning, it is can I automatically optimize my use case to perform better if I throw data at the problem? And fine-tuning is one of multiple ways to achieve that.”OpenAI vs Open AI Market ShareWe last speculated about the market shifts in the End of OpenAI Hegemony and the Winds of AI Winter, and Ankur’s perspective is super valuable given his customer list:Some surprises based on what he is seeing:* Prior to Claude 3, OpenAI had near 100% market share. This tracks with what Harrison told us last year.* Claude 3.5 Sonnet and also notably Haiku have made serious dents* Open source model adoption is <5% and DECLINING. Contra to Eugene Cheah’s ideal marketing pitch, virtually none of Braintrust’s customers are really finetuning open source models for cost, control, or privacy. This is partially caused by…* Open source model hosts, aka Inference providers, aren’t as mature as OpenAI’s API platform. Kudos to Michelle’s team as if they needed any more praise!* Adoption of Big Lab models via their Big Cloud Partners, aka Claude through AWS, or OpenAI through Azure, is low. Surprising! It seems that there are issues with accessing the latest models via the Cloud partners.swyx [01:36:51]: What % of your workload is open source?Ankur Goyal [01:36:55]: Because of how we're deployed, I don't have like an exact number for you. Among customers running in production, it's less than 5%.Full Video EpisodeCheck out the Braintrust demo on YouTube! (and like and subscribe etc)Show Notes* Ankur’s companies* MemSQL/SingleStore → now Nikita Shamgunov of Neon* Impira* Braintrust* Papers mentioned* AlexNet* BERT Paper* Layout LM Paper* GPT-3 Paper* Voyager Paper* AI Engineer World's Fair* Ankur and Olmo’s talk at AIEWF* Together.ai* Fireworks* People* Nikita Shamgunov* Alana Goyal* Elad Gil* Clem Delangue* Guillermo Rauch* Prior episodes* HumanLoop episode* Michelle Pokrass episode* Dylan Patel episodeTimestamps* [00:00:00] Introduction and background on Ankur career* [00:00:49] SingleStore and HTAP databases* [00:08:19] Founding Impira and lessons learned* [00:13:33] Unstructured vs Structured Data * [00:25:41] Overview of Braintrust and its features* [00:40:42] Industry observations and trends in AI tooling* [00:58:37] Workload types and AI use cases in production* [01:06:37] World's Fair AI conference discussion* [01:11:09] AI infrastructure market landscape* [01:24:59] OpenAI vs Anthropic vs other model providers* [01:38:11] GPU inference market discussion* [01:45:39] Hypothetical AI projects outside of Braintrust* [01:50:25] Potentially joining OpenAI* [01:52:37] Insights on effective networking and relationships in techTranscriptswyx [00:00:00]: Ankur Goyal, welcome to Latent Space.Ankur Goyal [00:00:06]: Thanks for having me.swyx [00:00:07]: Thanks for coming all the way over to our studio.Ankur Goyal [00:00:10]: It was a long hike.swyx [00:00:11]: A long trek. Yeah. You got T-boned by traffic. Yeah. You were the first VP of Eng at Signal Store. Yeah. Then you started Impira. You ran it for six years, got acquired into Figma, where you were at for eight months, and you just celebrated your one-year anniversary at Braintrust. I did, yeah. What a journey. I kind of want to go through each in turn because I have a personal relationship with Signal Store just because I have been a follower and fan of databases for a while. HTAP is always a dream of every database guy. It's still the dream. When HTAP, and Signal Store I think is the leading HTAP. Yeah. What's that journey like? And then maybe we'll cover the rest later.Ankur Goyal [00:00:49]: Sounds good.swyx [00:00:50]: We can start Signal Store first. Yeah, yeah.Ankur Goyal [00:00:52]: In college, as a first-generation Indian kid, I basically had two options. I had already told my parents I wasn't going to be a doctor. They're both doctors, so only two options left. Do a PhD or work at a big company. After my sophomore year, I worked at Microsoft, and it just wasn't for me. I realized that the work I was doing was impactful. I was working on Bing and the distributed compute infrastructure at Bing, which is actually now part of Azure. There were hundreds of engineers using the infrastructure that we were working on, but the level of intensity was too low. It felt like you got work-life balance and impact, but very little creativity, very little room to do interesting things. I was like, okay, let me cross that off the list. The only option left is to do research. I did research the next summer, and I realized, again, no one's working that hard. Maybe the times have changed, but at that point, there's a lot of creativity. You're just bouncing around fun ideas and working on stuff and really great work-life balance, but no one would actually use the stuff that we built, and that was not super energizing for me. I had this existential crisis, and I moved out to San Francisco because I had a friend who was here and crashed on his couch and was talking to him and just very, very confused. He said, you should talk to a recruiter, which felt like really weird advice. I'm not even sure I would give that advice to someone nowadays, but I met this really great guy named John, and he introduced me to like 30 different companies. I realized that there's actually a lot of interesting stuff happening in startups, and maybe I could find this kind of company that let me be very creative and work really hard and have a lot of impact, and I don't give a s**t about work-life balance. I talked to all these companies, and I remember I met MemSQL when it was three people and interviewed, and I thought I just totally failed the interview, but I had never had so much fun in my life. I remember I was at 10th and Harrison, and I stood at the bus station, and I called my parents and said, I'm sorry, I'm dropping out of school. I thought I wouldn't get the offer, but I just realized that if there's something like this company, then this is where I need to be. Luckily, things worked out, and I got an offer, and I joined as employee number two, and I worked there for almost six years, and it was an incredible experience. Learned a lot about systems, got to work with amazing customers. There are a lot of things that I took for granted that I later learned at Impira that I had taken for granted, and the most exciting thing is I got to run the engineering team, which was a great opportunity to learn about tech on a larger stage, recruit a lot of great people, and I think, for me personally, set me up to do a lot of interesting things after.swyx [00:03:41]: Yeah, there's so many ways I can take that. The most curious, I think, for general audiences is, is the dream real of SingleStore? Should, obviously, more people be using it? I think there's a lot of marketing from SingleStore that makes sense, but t
We all have fond memories of the first Dev Day in 2023:and the blip that followed soon after. As Ben Thompson has noted, this year’s DevDay took a quieter, more intimate tone. No Satya, no livestream, (slightly fewer people?). Instead of putting ChatGPT announcements in DevDay as in 2023, o1 was announced 2 weeks prior, and DevDay 2024 was reserved purely for developer-facing API announcements, primarily the Realtime API, Vision Finetuning, Prompt Caching, and Model Distillation.However the larger venue and more spread out schedule did allow a lot more hallway conversations with attendees as well as more community presentations including our recent guest Alistair Pullen of Cosine as well as deeper dives from OpenAI including our recent guest Michelle Pokrass of the API Team. Thanks to OpenAI’s warm collaboration (we particularly want to thank Lindsay McCallum Rémy!), we managed to record exclusive interviews with many of the main presenters of both the keynotes and breakout sessions. We present them in full in today’s episode, together with a full lightly edited Q&A with Sam Altman.Show notes and related resourcesSome of these used in the final audio episode below* Simon Willison Live Blog* swyx live tweets and videos* Greg Kamradt coverage of Structured Output session, Scaling LLM Apps session* Fireside Chat Q&A with Sam AltmanTimestamps* [00:00:00] Intro by Suno.ai* [00:01:23] NotebookLM Recap of DevDay* [00:09:25] Ilan's Strawberry Demo with Realtime Voice Function Calling* [00:19:16] Olivier Godement, Head of Product, OpenAI* [00:36:57] Romain Huet, Head of DX, OpenAI* [00:47:08] Michelle Pokrass, API Tech Lead at OpenAI ft. Simon Willison* [01:04:45] Alistair Pullen, CEO, Cosine (Genie)* [01:18:31] Sam Altman + Kevin Weill Q&A* [02:03:07] Notebook LM Recap of PodcastTranscript[00:00:00] Suno AI: Under dev daylights, code ignites. Real time voice streams reach new heights. O1 and GPT, 4. 0 in flight. Fine tune the future, data in sight. Schema sync up, outputs precise. Distill the models, efficiency splice.[00:00:33] AI Charlie: Happy October. This is your AI co host, Charlie. One of our longest standing traditions is covering major AI and ML conferences in podcast format. Delving, yes delving, into the vibes of what it is like to be there stitched in with short samples of conversations with key players, just to help you feel like you were there.[00:00:54] AI Charlie: Covering this year's Dev Day was significantly more challenging because we were all requested not to record the opening keynotes. So, in place of the opening keynotes, we had the viral notebook LM Deep Dive crew, my new AI podcast nemesis, Give you a seven minute recap of everything that was announced.[00:01:15] AI Charlie: Of course, you can also check the show notes for details. I'll then come back with an explainer of all the interviews we have for you today. Watch out and take care.[00:01:23] NotebookLM Recap of DevDay[00:01:23] NotebookLM: All right, so we've got a pretty hefty stack of articles and blog posts here all about open ais. Dev day 2024.[00:01:32] NotebookLM 2: Yeah, lots to dig into there.[00:01:34] NotebookLM 2: Seems[00:01:34] NotebookLM: like you're really interested in what's new with AI.[00:01:36] NotebookLM 2: Definitely. And it seems like OpenAI had a lot to announce. New tools, changes to the company. It's a lot.[00:01:43] NotebookLM: It is. And especially since you're interested in how AI can be used in the real world, you know, practical applications, we'll focus on that.[00:01:51] NotebookLM: Perfect. Like, for example, this Real time API, they announced that, right? That seems like a big deal if we want AI to sound, well, less like a robot.[00:01:59] NotebookLM 2: It could be huge. The real time API could completely change how we, like, interact with AI. Like, imagine if your voice assistant could actually handle it if you interrupted it.[00:02:08] NotebookLM: Or, like, have an actual conversation.[00:02:10] NotebookLM 2: Right, not just these clunky back and forth things we're used to.[00:02:14] NotebookLM: And they actually showed it off, didn't they? I read something about a travel app, one for languages. Even one where the AI ordered takeout.[00:02:21] NotebookLM 2: Those demos were really interesting, and I think they show how this real time API can be used in so many ways.[00:02:28] NotebookLM 2: And the tech behind it is fascinating, by the way. It uses persistent WebSocket connections and this thing called function calling, so it can respond in real time.[00:02:38] NotebookLM: So the function calling thing, that sounds kind of complicated. Can you, like, explain how that works?[00:02:42] NotebookLM 2: So imagine giving the AI Access to this whole toolbox, right?[00:02:46] NotebookLM 2: Information, capabilities, all sorts of things. Okay. So take the travel agent demo, for example. With function calling, the AI can pull up details, let's say about Fort Mason, right, from some database. Like nearby restaurants, stuff like that.[00:02:59] NotebookLM: Ah, I get it. So instead of being limited to what it already knows, It can go and find the information it needs, like a human travel agent would.[00:03:07] NotebookLM 2: Precisely. And someone on Hacker News pointed out a cool detail. The API actually gives you a text version of what's being said. So you can store that, analyze it.[00:03:17] NotebookLM: That's smart. It seems like OpenAI put a lot of thought into making this API easy for developers to use. But, while we're on OpenAI, you know, Besides their tech, there's been some news about, like, internal changes, too.[00:03:30] NotebookLM: Didn't they say they're moving away from being a non profit?[00:03:32] NotebookLM 2: They did. And it's got everyone talking. It's a major shift. And it's only natural for people to wonder how that'll change things for OpenAI in the future. I mean, there are definitely some valid questions about this move to for profit. Like, will they have more money for research now?[00:03:46] NotebookLM 2: Probably. But will they, you know, care as much about making sure AI benefits everyone?[00:03:51] NotebookLM: Yeah, that's the big question, especially with all the, like, the leadership changes happening at OpenAI too, right? I read that their Chief Research Officer left, and their VP of Research, and even their CTO.[00:04:03] NotebookLM 2: It's true. A lot of people are connecting those departures with the changes in OpenAI's structure.[00:04:08] NotebookLM: And I guess it makes you wonder what's going on behind the scenes. But they are still putting out new stuff. Like this whole fine tuning thing really caught my eye.[00:04:17] NotebookLM 2: Right, fine tuning. It's essentially taking a pre trained AI model. And, like, customizing it.[00:04:23] NotebookLM: So instead of a general AI, you get one that's tailored for a specific job.[00:04:27] NotebookLM 2: Exactly. And that opens up so many possibilities, especially for businesses. Imagine you could train an AI on your company's data, you know, like how you communicate your brand guidelines.[00:04:37] NotebookLM: So it's like having an AI that's specifically trained for your company?[00:04:41] NotebookLM 2: That's the idea.[00:04:41] NotebookLM: And they're doing it with images now, too, right?[00:04:44] NotebookLM: Fine tuning with vision is what they called it.[00:04:46] NotebookLM 2: It's pretty incredible what they're doing with that, especially in fields like medicine.[00:04:50] NotebookLM: Like using AI to help doctors make diagnoses.[00:04:52] NotebookLM 2: Exactly. And AI could be trained on thousands of medical images, right? And then it could potentially spot things that even a trained doctor might miss.[00:05:03] NotebookLM: That's kind of scary, to be honest. What if it gets it wrong?[00:05:06] NotebookLM 2: Well, the idea isn't to replace doctors, but to give them another tool, you know, help them make better decisions.[00:05:12] NotebookLM: Okay, that makes sense. But training these AI models must be really expensive.[00:05:17] NotebookLM 2: It can be. All those tokens add up. But OpenAI announced something called automatic prompt caching.[00:05:23] Alex Volkov: Automatic what now? I don't think I came across that.[00:05:26] NotebookLM 2: So basically, if your AI sees a prompt that it's already seen before, OpenAI will give you a discount.[00:05:31] NotebookLM: Huh. Like a frequent buyer program for AI.[00:05:35] NotebookLM 2: Kind of, yeah. It's good that they're trying to make it more affordable. And they're also doing something called model distillation.[00:05:41] NotebookLM: Okay, now you're just using big words to sound smart. What's that?[00:05:45] NotebookLM 2: Think of it like like a recipe, right? You can take a really complex recipe and break it down to the essential parts.[00:05:50] NotebookLM: Make it simpler, but it still tastes the same.[00:05:53] NotebookLM 2: Yeah. And that's what model distillation is. You take a big, powerful AI model and create a smaller, more efficient version.[00:06:00] NotebookLM: So it's like lighter weight, but still just as capable.[00:06:03] NotebookLM 2: Exactly. And that means more people can actually use these powerful tools. They don't need, like, a supercomputer to run them.[00:06:10] NotebookLM: So they're making AI more accessible. That's great.[00:06:13] NotebookLM 2: It is. And speaking of powerful tools, they also talked about their new O1 model.[00:06:18] NotebookLM 2: That's the one they've been hyping up. The one that's supposed to be this big leap forward.[00:06:22] NotebookLM: Yeah, O1. It sounds pretty futuristic. Like, from what I read, it's not just a bigger, better language model.[00:06:28] NotebookLM 2: Right. It's a different porch.[00:06:29] NotebookLM: They're saying it can, like, actually reason, right? Think.[00:06:33] NotebookLM 2: It's trained differently.[00:06:34] NotebookLM 2: They used reinforcement learning with O1.[00:06:36] NotebookLM: So it's
OpenAI DevDay is almost here! Per tradition, we are hosting a DevDay pregame event for everyone coming to town! Join us with demos and gossip!Also sign up for related events across San Francisco: the AI DevTools Night, the xAI open house, the Replicate art show, the DevDay Watch Party (for non-attendees), Hack Night with OpenAI at Cloudflare. For everyone else, join the Latent Space Discord for our online watch party and find fellow AI Engineers in your city.OpenAI’s recent o1 release (and Reflection 70b debacle) has reignited broad interest in agentic general reasoning and tree search methods.While we have covered some of the self-taught reasoning literature on the Latent Space Paper Club, it is notable that the Eric Zelikman ended up at xAI, whereas OpenAI’s hiring of Noam Brown and now Shunyu suggests more interest in tool-using chain of thought/tree of thought/generator-verifier architectures for Level 3 Agents.We were more than delighted to learn that Shunyu is a fellow Latent Space enjoyer, and invited him back (after his first appearance on our NeurIPS 2023 pod) for a look through his academic career with Harrison Chase (one year after his first LS show).ReAct: Synergizing Reasoning and Acting in Language Modelspaper linkFollowing seminal Chain of Thought papers from Wei et al and Kojima et al, and reflecting on lessons from building the WebShop human ecommerce trajectory benchmark, Shunyu’s first big hit, the ReAct paper showed that using LLMs to “generate both reasoning traces and task-specific actions in an interleaved manner” achieved remarkably greater performance (less hallucination/error propagation, higher ALFWorld/WebShop benchmark success) than CoT alone. In even better news, ReAct scales fabulously with finetuning:As a member of the elite Princeton NLP group, Shunyu was also a coauthor of the Reflexion paper, which we discuss in this pod.Tree of Thoughtspaper link hereShunyu’s next major improvement on the CoT literature was Tree of Thoughts:Language models are increasingly being deployed for general problem solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during inference. This means they can fall short in tasks that require exploration, strategic lookahead, or where initial decisions play a pivotal role…ToT allows LMs to perform deliberate decision making by considering multiple different reasoning paths and self-evaluating choices to decide the next course of action, as well as looking ahead or backtracking when necessary to make global choices.The beauty of ToT is it doesnt require pretraining with exotic methods like backspace tokens or other MCTS architectures. You can listen to Shunyu explain ToT in his own words on our NeurIPS pod, but also the ineffable Yannic Kilcher:Other WorkWe don’t have the space to summarize the rest of Shunyu’s work, you can listen to our pod with him now, and recommend the CoALA paper and his initial hit webinar with Harrison, today’s guest cohost:as well as Shunyu’s PhD Defense Lecture:as well as Shunyu’s latest lecture covering a Brief History of LLM Agents:As usual, we are live on YouTube! Show Notes* Harrison Chase* LangChain, LangSmith, LangGraph* Shunyu Yao* Alec Radford* ReAct Paper* Hotpot QA* Tau Bench* WebShop* SWE-Agent* SWE-Bench* Trees of Thought* CoALA Paper* Related Episodes* Our Thomas Scialom (Meta) episode* Shunyu on our NeurIPS 2023 Best Papers episode* Harrison on our LangChain episode* Mentions* Sierra* Voyager* Jason Wei* Tavily* SERP API* ExaTimestamps* [00:00:00] Opening Song by Suno* [00:03:00] Introductions* [00:06:16] The ReAct paper* [00:12:09] Early applications of ReAct in LangChain* [00:17:15] Discussion of the Reflection paper* [00:22:35] Tree of Thoughts paper and search algorithms in language models* [00:27:21] SWE-Agent and SWE-Bench for coding benchmarks* [00:39:21] CoALA: Cognitive Architectures for Language Agents* [00:45:24] Agent-Computer Interfaces (ACI) and tool design for agents* [00:49:24] Designing frameworks for agents vs humans* [00:53:52] UX design for AI applications and agents* [00:59:53] Data and model improvements for agent capabilities* [01:19:10] TauBench* [01:23:09] Promising areas for AITranscriptAlessio [00:00:01]: Hey, everyone, welcome to the Latent Space podcast. This is Alessio, partner and CTO of Residence at Decibel Partners, and I'm joined by my co-host Swyx, founder of Small AI.Swyx [00:00:12]: Hey, and today we have a super special episode. I actually always wanted to take like a selfie and go like, you know, POV, you're about to revolutionize the world of agents because we have two of the most awesome hiring agents in the house. So first, we're going to welcome back Harrison Chase. Welcome. Excited to be here. What's new with you recently in sort of like the 10, 20 second recap?Harrison [00:00:34]: Linkchain, Linksmith, Lingraph, pushing on all of them. Lots of cool stuff related to a lot of the stuff that we're going to talk about today, probably.Swyx [00:00:42]: Yeah.Alessio [00:00:43]: We'll mention it in there. And the Celtics won the title.Swyx [00:00:45]: And the Celtics won the title. You got that going on for you. I don't know. Is that like floorball? Handball? Baseball? Basketball.Alessio [00:00:52]: Basketball, basketball.Harrison [00:00:53]: Patriots aren't looking good though, so that's...Swyx [00:00:56]: And then Xun Yu, you've also been on the pod, but only in like a sort of oral paper presentation capacity. But welcome officially to the LinkedSpace pod.Shunyu [00:01:03]: Yeah, I've been a huge fan. So thanks for the invitation. Thanks.Swyx [00:01:07]: Well, it's an honor to have you on. You're one of like, you're maybe the first PhD thesis defense I've ever watched in like this AI world, because most people just publish single papers, but every paper of yours is a banger. So congrats.Shunyu [00:01:22]: Thanks.Swyx [00:01:24]: Yeah, maybe we'll just kick it off with, you know, what was your journey into using language models for agents? I like that your thesis advisor, I didn't catch his name, but he was like, you know... Karthik. Yeah. It's like, this guy just wanted to use language models and it was such a controversial pick at the time. Right.Shunyu [00:01:39]: The full story is that in undergrad, I did some computer vision research and that's how I got into AI. But at the time, I feel like, you know, you're just composing all the GAN or 3D perception or whatever together and it's not exciting anymore. And one day I just see this transformer paper and that's really cool. But I really got into language model only when I entered my PhD and met my advisor Karthik. So he was actually the second author of GPT-1 when he was like a visiting scientist at OpenAI. With Alec Redford?Swyx [00:02:10]: Yes.Shunyu [00:02:11]: Wow. That's what he told me. It's like back in OpenAI, they did this GPT-1 together and Ilya just said, Karthik, you should stay because we just solved the language. But apparently Karthik is not fully convinced. So he went to Princeton, started his professorship and I'm really grateful. So he accepted me as a student, even though I have no prior knowledge in NLP. And you know, we just met for the first time and he's like, you know, what do you want to do? And I'm like, you know, you have done those test game scenes. That's really cool. I wonder if we can just redo them with language models. And that's how the whole journey began. Awesome.Alessio [00:02:46]: So GPT-2 was out at the time? Yes, that was 2019.Shunyu [00:02:48]: Yeah.Alessio [00:02:49]: Way too dangerous to release. And then I guess the first work of yours that I came across was React, which was a big part of your defense. But also Harrison, when you came on The Pockets last year, you said that was one of the first papers that you saw when you were getting inspired for BlankChain. So maybe give a recap of why you thought it was cool, because you were already working in AI and machine learning. And then, yeah, you can kind of like intro the paper formally. What was that interesting to you specifically?Harrison [00:03:16]: Yeah, I mean, I think the interesting part was using these language models to interact with the outside world in some form. And I think in the paper, you mostly deal with Wikipedia. And I think there's some other data sets as well. But the outside world is the outside world. And so interacting with things that weren't present in the LLM and APIs and calling into them and thinking about the React reasoning and acting and kind of like combining those together and getting better results. I'd been playing around with LLMs, been talking with people who were playing around with LLMs. People were trying to get LLMs to call into APIs, do things, and it was always, how can they do it more reliably and better? And so this paper was basically a step in that direction. And I think really interesting and also really general as well. Like I think that's part of the appeal is just how general and simple in a good way, I think the idea was. So that it was really appealing for all those reasons.Shunyu [00:04:07]: Simple is always good. Yeah.Alessio [00:04:09]: Do you have a favorite part? Because I have one favorite part from your PhD defense, which I didn't understand when I read the paper, but you said something along the lines, React doesn't change the outside or the environment, but it does change the insight through the context, putting more things in the context. You're not actually changing any of the tools around you to work for you, but you're changing how the model thinks. And I think that was like a very profound thing when I, not that I've been using these tools for like 18 months. I'm like, I understand what you meant, but like to say that at the time you did the PhD defense was not trivial. Yeah.Shunyu [00:04:41]: Another way to put it is like thinking can be an extra tool that's useful.Alessio [00:04:47]: Makes sense. Checks