Better Stack Podcast

In this episode of the Better Stack Podcast, we sit down with Hao Sheng, founder of Expertise.ai, to talk about how AI can transform the way businesses interact with their customers. Hao shares his journey from building early chatbot systems at Google to creating “human business interfaces” that turn static websites into dynamic, personalized experiences. We also explore what’s next for conversational AI and Hao’s vision for the future of human–AI interaction.

In this episode of the Better Stack podcast, Richard, James, and Andris are joined by Beto, a Developer Success Engineer at Expo. They discuss Beto's role at Expo, the benefits of using Expo for React Native development, and the future of Expo. Beto shares insights about over-the-air updates, the CI/CD pipeline for app deployment, and his journey from Walmart to Expo. The conversation also covers content creation, including Beto's YouTube journey, his audio and video setup, and the tools he uses for editing. The episode concludes with a discussion on the challenges of app development for foldable devices and Beto's spicy take on Flutter.

Join James, Richard, and Andris as they dive deep into the explosive ChatGPT-5 release that left developers fuming! Discover why the "PhD-level coding AI" fell flat in real-world tests, the controversial router system that routes to older models, and how OpenAI's Apple-style marketing backfired spectacularly. Then buckle up for a wild ride through the AI coding tools battlefield—why Claude Code is crushing the competition, the shocking truth about benchmark manipulation, and which CLI tools are actually worth your time. Finally, explore the chaotic world of AI agent protocols where everyone's trying to create the next MCP, featuring crypto-wallet AI disasters and the dystopian future where AI browsers might kill the internet economy as we know it!

In this episode, Evan You, creator of Vue.js and Vite, shares his journey from building Vite to founding VoidZero and developing a complete Rust-based JavaScript toolchain. He discusses the evolution from Vite's ESBuild+Rollup hybrid to Rolldown, the 50-100x performance gains with OXC (linter, formatter, parser), and how Vite Plus aims to simplify the entire JavaScript onboarding experience. Evan also shares his thoughts on the future of bundling vs no-build approaches, why his team chose Rust over Go, how they're using AI to ship features faster while maintaining code quality, and offers a candid take on React Server Components as a long-time skeptic who believes the trade-offs often outweigh the benefits.Link:Do we need bundlers - https://rolldown.rs/in-depth/why-bundlers

In this episode, Bashbunni shares her journey from mastering terminal tools to joining (and leaving) Charm, to building inclusive coding communities. She discusses her transition from Vim to Doom Emacs, the impact of AI on coding education, and why balancing shortcuts with hands-on learning is crucial for developer growth. Bash also loves to coding in public and she regularly streams to encourage more people to code along with her and also to give her tips on what she can do to improve her Linux setup. Link:Bashbunni - https://www.bashbunni.dev/Charm - https://charm.land/VScode vim plugin - https://marketplace.visualstudio.com/items?itemName=vscodevim.vimSeven Languages in Seven Weeks - https://www.amazon.co.uk/Seven-Languages-Weeks-Programming-Programmers/dp/193435659XDoom Emacs - https://github.com/doomemacs/doomemacsLearn X in Y minutes - https://learnxinyminutes.com/The Pragmatic Programmer - https://www.amazon.co.uk/Pragmatic-Programmer-Andrew-Hunt/dp/020161622X

Join David Flanagan, founder of Raw Code Academy and 20-year cloud native veteran, as he shares his journey of building a completely over-engineered education platform using GraphQL Federation, Cloudflare Workers, and extreme microservices architecture. Discover how he's creating developer content for senior engineers, runs a one-man business powered by AI agents, and maintains his sanity with Jack Daniels (sometimes). Plus, hear his spicy takes on Kubernetes being both the best and worst thing in platform engineering, why AI makes junior developers obsolete, and why manual testing beats automated tests in 2025. From terminal workflows to mechanical keyboards, this is the raw truth about modern software development.

In this conversation, Sarah Benson discusses the current state of Web3 and crypto, emphasizing that the industry is not dead but has matured significantly. She highlights the evolving role of blockchain as a foundational infrastructure layer in various applications, particularly in the context of emerging technologies like AI.

In this episode, we sit down with Ben, the founder and engineer behind Spec - an OS-level AI assistant for your Mac. Ben shares how he built Spec almost entirely himself, why he pivoted from robotics to personal AI, and what he’s learned across his previous startups. We cover Spec’s architecture, privacy model, and the future of “personal intelligence.” If you’re a developer or founder curious about practical AI tools, this one’s for you.🔗 Relevant LinksSpec: https://withspec.com/Ben (X): https://x.com/benktaytay❤️ More about usRadically better observability stack: https://betterstack.com/Written tutorials: https://betterstack.com/community/Example projects: https://github.com/BetterStackHQ

In this episode of the Better Stack Podcast, James, Richard, and Andris delve into the latest developments in AI, focusing on OpenAI's Sora 2 video model and its features, including the cameo function. They discuss the invite process for accessing Sora 2, user experiences with video generation, and the implications of copyright and training data. The conversation shifts to the business model behind Sora 2, comparisons with other video generation models, and the future of AI agents with the Claude SDK. Ethical considerations regarding AI's impact on the environment and the potential success of Sora 2 in the market are also explored.

In this episode, we dive deep into MCP UI - the revolutionary technology that could transform ChatGPT from a text-only experience to a rich, interactive interface where brands can bring their own UI components directly into AI conversations. We explore the implications for e-commerce, user experience, and whether this is the future of human-AI interaction or just over-engineering. Plus, we discuss the next frontier: Large Behavioral Models that are powering the new generation of humanoid robots from companies like Helix, Tesla's Optimus, and Boston Dynamics, and examine how these advances might soon bring robotics into our everyday lives.

In this episode of the Better Stack Podcast, the team dives into the latest developments in AI tooling and models. They explore the new AI SDK and AI Elements library, discuss the stealth release of Sonic (aka Grok’s CodeFast), and break down OpenAI’s GPT real-time API and its potential uses. Andris takes us behind the scenes of LLMs, sharing the hilarious Golden Gate Bridge neuron story and his own quest to create a Chuck Norris model. The crew also debates AGI hype, jailbreak exploits, and wraps things up with some surprisingly tricky JavaScript date trivia.