Lenny’s AI Builders

Kimi K3.1 Pro just dropped, so i gave it and Opus 5.5 the exact same prompt: build me a 3D game where you're a Perth plumber racing to call-outs. one game cost $1.08, the other $3.21 (API-equivalent, one shot each), and only one of them got Perth. i play both blind before i tell you which model built which. also this week: OpenAI paused its best models for 11 days after a settings mistake gave one a little bit of internet during training, Cursor's agents can now drive your whole computer, Block's Dessa is the most human AI voice i've heard (waitlist only), and Grok Bot's new Vault can sign in and check out for you. the practical - one prompt that makes your site work on the iPhone Duo's big inner screen. paste it into Claude Code inside your project. it screenshots every page at the Duo sizes before it changes anything, writes a check that fails first, fixes it until it passes, and leaves your normal phone and desktop layouts alone. on my site, 9 checks failed before the fix and all 18 passed after. the catch: those Duo sizes come from a simulator, not Apple, so measure your own Duo first and put your numbers in the prompt. the prompt: make this site work well on the iphone duo's big inner screen. work on a new git branch, draft only: never push, merge or deploy. 1. find every width breakpoint in the code and list them. 2. run the app locally. with playwright, screenshot every main page at 382x580, 669x825, 870x669, 951x543, plus a normal phone (390x844) and desktop (1440x900), before changing anything. save them in a before folder. 3. add a fold layout for screens roughly 600 to 1000px wide. where the app has a list plus detail, or a sidebar, show two panes side by side. make every tap target at least 44px, make sure nothing hides under fixed buttons, and respect safe-area insets (left and right). 4. write a playwright check for those rules (no sideways scroll, tap targets, two panes). run it first and show it failing. then make the fix and show it passing. 5. screenshot the same sizes again into an after folder. the 390x844 and 1440x900 layouts must not change at all. 6. finish with a before/after table: size, what was wrong, what changed. links Kimi K3.1 Pro launch: https://x.com/Kimi_Moonshot/status/2113680701770068067 OpenAI on securing its training environment: https://openai.com/index/securing-our-frontier-model-training-environment/ OpenAI on the Hugging Face incident: https://openai.com/index/hugging-face-incident-and-the-road-ahead/ Cursor's agents can drive your computer: https://x.com/cursor_ai/status/2113661506634305834 Jack Dorsey on Dessa: https://x.com/jack/status/2113697902916751661 Dessa waitlist: https://block.xyz/dessa Grok Bot's Vault: https://x.com/bot/status/2113717946019397910 Grok Bot changelog: https://x.ai/changelog/bot Marc Lou's site on the iPhone Duo: https://x.com/marclou/status/2113588729675694385 Greg Isenberg on Duo apps: https://x.com/gregisenberg/status/2113271458168279286 chapters 0:00 two models, one prompt, one game 0:13 Kimi K3.1 vs Opus 5.5: the blind test 3:07 Lenny's AI Builders 3:21 agents are getting hands 3:42 OpenAI's agents broke out of the box 5:17 Cursor can drive your computer 6:27 sponsor: Threadify 7:41 Dessa: voice agents woke up 9:15 Grok Bot can check out for you 10:43 your site is broken on the iPhone Duo 12:06 the prompt: make your site work on the Duo 13:37 see you next episode thanks to today's sponsor, my software Threadify - your lead generation agent for Threads, X and YouTube. my agents run it for me straight from Claude, and nothing goes out until i say yes. start your free 7-day trial: https://www.threadify.app/home?utm_source=youtube&utm_medium=video&utm_campaign=lab-0029&utm_content=sponsor&video_slug=lab-0029&cta_slot=youtube_description&entry_angle=agent_mcp want to sponsor a future episode? [email protected] watch the full episode: https://www.youtube.com/watch?v=6LmucdqB0wU

Claude Slides is now in every Claude chat, even on the free plan, and ChatGPT Slides just got live collab on Pro. so i gave both the exact same job - a 10-slide client pitch deck from one page of notes - twice each. then a free GitHub skill called frontend-slides crashed the fight in Claude Code. six decks, letters A to F, no names, and a blind judge from a different AI scored them before i looked. the loser costs me my ChatGPT plan. also this week: Meta's Muse Glimmer open model for your own computer, Anthropic's new Public Benefit Fund (and Elon's reply), Claude's free OSS Scanner for open source projects, Grok Bot on the iPhone Action Button, Tibo's day 14 update, and The Information's report on Anthropic's next model. the practical: make your decks look designed with frontend-slides (free, in Claude Code): 1. /plugin marketplace add https://github.com/zarazhangrui/frontend-slides 2. /plugin install frontend-slides@frontend-slides 3. /frontend-slides - paste your notes or a call transcript, then pick a style you get one web page deck, and you can export it as a PDF. links Boris Cherny on Claude Slides: https://x.com/bcherny/status/2111158659971699136 Claude Docs, Slides and Design in every chat: https://x.com/bcherny/status/2100260544087535639 ChatGPT Slides update: https://x.com/ChatGPT/status/2112265233192657153 frontend-slides on GitHub: https://github.com/zarazhangrui/frontend-slides Muse Glimmer: https://dev.meta.ai/models/muse-glimmer/ Muse Glimmer report from AI at Meta: https://x.com/AIatMeta/status/2112265822274302066 Anthropic Public Benefit Fund: https://www.anthropic.com/news/public-benefit-fund Anthropic's post: https://x.com/AnthropicAI/status/2111881963657412903 Elon Musk's reply: https://x.com/elonmusk/status/2111914396490604547 Elon Musk on SpaceX shares: https://x.com/elonmusk/status/2112089556615123114 OSS Scanner: https://red.anthropic.com/oss-scanner OSS Scanner launch post: https://x.com/ClaudeDevs/status/2112299602510749992 Grok Bot Action Button: https://x.com/bot/status/2112252507762368684 Tibo day 14: https://x.com/thsottiaux/status/2111990254408434095 The Information on Anthropic's next model: https://x.com/theinformation/status/2112212326795362560 chapters 0:00 the bet: the loser costs me my ChatGPT plan 0:20 Claude Slides vs ChatGPT Slides 1:49 this is the LAB 2:22 Muse Glimmer 30B goes open 3:08 Anthropic's 5% fund - and Elon in the replies 4:50 sponsor: Threadify 5:56 Claude's free open-source scanner 6:57 Grok Bot on the Action Button 8:43 Anthropic's next model 10:09 the free skill that makes decks look designed 11:05 the blind verdict 12:56 the live cancel 13:25 was he right? thanks to today's sponsor, my software Threadify - your lead generation agent: https://www.threadify.app/home?utm_source=youtube&utm_medium=video&utm_campaign=lab-0025&utm_content=sponsor&video_slug=lab-0025&cta_slot=youtube_description&entry_angle=lead_signal want to sponsor a future episode? [email protected] watch the full episode: https://youtu.be/f8WKH7fFL6Q

PHP got hacked wide open this week - two critical bugs that let anyone take over a PHP server without logging in. the same day LiteLLM 1.107.0 shipped a password stealer, and Railway, where my app runs, got broken into. so i gave Claude one prompt to check my Mac and my websites for all three. PHP: clear. LiteLLM: clear. Railway: hit. Threadify runs on it, and Claude found Railway's warning email sitting unopened in my inbox. we'd already handled it, but that's the one that mattered. also this week: Claude Duet, an agent that comes to you (waitlist, US Pro and Max), Andrew Curran says OpenAI calls the PHP bug the tip of the iceberg, Claude Security now re-scans as your code changes (Enterprise beta), Tibo's reset day, editing with no editor, and the one line that makes your Claude Projects coordinator report in. the practical - check if this week's hacks hit you, in one prompt. paste it into Claude Code and swap in your own websites at the end: This week PHP had two critical bugs (fixed in PHP 8.5.12, 8.4.27, 8.3.36 and 8.2.35), LiteLLM 1.107.0 shipped a password stealer, and Railway asked everyone to rotate their keys. Check my computer and my websites for all three. Only look, change nothing, and never show me a password or key. Then tell me in plain English: am I affected, how bad is it, and the one thing to do first. My websites: yoursite.com it only looks and changes nothing. the catch: it can only check what it can see, so you still read it with your own eyes. if you run a website, update PHP or ask whoever hosts it if they have. if you use Railway, swap your keys - new one in first, then turn the old one off. want to join the beta of the agentic video editor i'm building? comment Eddy below. links fiveoutofnine on PHP's week: https://x.com/fiveoutofnine/status/2113045722744717360 Claude Duet: https://x.com/claudeai/status/2112984664256241837 Andrew Curran on OpenAI's tip of the iceberg: https://x.com/AndrewCurran_/status/2112913197774807491 Claude Security scans continuously: https://x.com/claudeai/status/2112962248218148878 Alex on editing headless: https://x.com/The_Alex/status/2112708662288625765 Anthony on making your coordinator report in: https://x.com/kr0der/status/2106429105671643587 chapters 0:00 PHP got hacked: am i hit? 2:40 Claude Duet comes to you 4:12 OpenAI: the tip of the iceberg 5:48 sponsor: Threadify 7:07 Claude Security keeps scanning 8:17 Tibo's reset day 8:56 editing with no editor 10:14 make your coordinator report in 12:11 check if you're hit, in one prompt thanks to today's sponsor, my software Threadify - your lead generation agent for Threads, X and YouTube: https://www.threadify.app/home?utm_source=youtube&utm_medium=video&utm_campaign=lab-0027&utm_content=sponsor&video_slug=lab-0027&cta_slot=youtube_description&entry_angle=lead_signal want to sponsor a future episode? [email protected] watch the full episode: https://www.youtube.com/watch?v=l6rSOfIZk_Y

four Shorts. two of them were made by Claude from one prompt, with my cloned voice and my AI face. pick your two letters in the comments before the reveal. if most of you can't tell, Claude makes every LAB Short for a month. also this week: Codex now keeps your chats cached forever (and why my Claude Max plan kept draining), Anthropic's draft IPO filing ($16.3 billion in revenue, and an $80 billion loss that's mostly paper), Dario's huge reply to his critic, one brain for all your agents with a lock so they stop tripping over each other, and the Grok Bot trick that gives every job its own email address. the practical: how Claude made a Short of me from one prompt for about $12.65: 1. it scrapes Shorts that are beating their channel's average, so the hook comes from what's working right now 2. it writes the script from facts you give it, and learns how you talk from your old captions 3. your voice, from your ElevenLabs clone 4. your face, from HeyGen, synced to that voice 5. it edits it in your Short style, captions and proof on screen 6. it checks it: a screenshot of every beat, fixes what looks off, checks sync and loudness the catch: you need your own voice clone and face set up first, and you still check every fact. the full prompt is in the field notes: https://lennoxsaint.com/lab/0026 links Riley Brown's one-prompt Claude edit: https://x.com/rileybrown/status/2111925755215040779 Theo on Codex keeping chats cached: https://x.com/theo/status/2112713481946570967 WSJ on Anthropic's draft IPO filing: https://x.com/WSJ/status/2112628141814358283 Dario Amodei's reply: https://x.com/darioamodei/status/2112732230124818891 Corey Ganim on one brain for your agents: https://x.com/coreyganim/status/2111490096402677760 the Grok Bot email trick: https://x.com/ManaEngineer/status/2112481479158587884 chapters 0:00 four Shorts, two made by Claude 0:22 Riley Brown's one-prompt Short 1:00 AI is doing more (the catch) 1:20 why my Claude Max plan drained 3:42 Anthropic's revenue: i was wrong 4:52 sponsor: Threadify 6:01 Dario hits back at his critic 7:44 my brain has a library card 9:49 give your Grok Bot its own email 10:58 how Claude made a Short of me for $12.65 12:46 last call: pick your two 13:21 the reveal 14:24 outro thanks to today's sponsor, my software Threadify - your lead generation agent: https://www.threadify.app/home?utm_source=youtube&utm_medium=video&utm_campaign=lab-0026&utm_content=sponsor&video_slug=lab-0026&cta_slot=youtube_description&entry_angle=voice_brain want to sponsor a future episode? [email protected] watch the full episode: https://www.youtube.com/watch?v=1Jvl7KxMfwA

devs are paying double for the old GPT on the API - GPT-5.6 Sol costs $4 in / $20 out per million tokens, GPT-6.1 Sol $2 / $10 - and swearing it's better than the new one. so i ran both on three of my real jobs (a broken test in Threadify, a video pipeline bug and my landing page copy), two runs each, with a blind judge from a different AI that only saw A and B. also this week: GPT-6 Pro running agents in parallel, Claude writing 90% of Claude Code, X paying creators to post video, Claude Code answering sooner, and moving your AI memory into Grok Bot. the practical: run your own model bake-off on your own work. give the prompt below to your agent. my recording cut out before i read it on camera, so here it is in full: I want to know which AI model is actually better for MY work - not on benchmarks. Run a blind bake-off. The job: [paste one real task from your week - a bug, a failing test, a page of copy] Model A: gpt-5.6-sol Model B: gpt-6.1-sol (swap in any two models your CLI can run) Prices per million tokens (OpenAI pricing page, 17 Oct 2026): gpt-5.6-sol $4 in / $0.40 cached / $20 out; gpt-6.1-sol $2 in / $0.10 cached / $10 out. 1. Make two clean copies of this project in a temp folder. Never touch my real folder. 2. Run the job once in each copy with the same prompt and the same effort setting: codex exec -m [model] -c model_reasoning_effort=medium --json "[the job]" Time each run and save its token usage. 3. Run my tests in both copies and note what passed. 4. Hide the model names. Label the two results A and B in a random order. Ask a different AI to judge them (for example: claude -p) - give it only the job, the two diffs and the test results, and ask for a 0-100 score and one sentence why for each. 5. Show me one table: tests passed, judge score, minutes, and cost at today's API prices. Then tell me which model to use for this kind of job - and say plainly if it's too close to call. Drafts only: don't push, merge or publish anything. chapters 0:00 devs pay double for the old GPT 0:11 my blind bake-off: 3 real jobs, 2 models 0:34 why devs went back to the 2x model 1:38 this is the LAB 1:54 stop reading benchmarks 2:13 GPT-6 Pro runs agents in parallel 4:21 Claude writes 90% of Claude Code 6:38 sponsor: Threadify 7:53 X pays creators to post video 9:22 more Codex usage, but no number 10:02 Claude Code answers sooner 10:54 move your AI memory into Grok Bot 11:55 run your own model bake-off 12:42 who won: old GPT vs new GPT 13:44 the prompt (full text below) thanks to today's sponsor, my software Threadify - your lead generation agent: https://www.threadify.app/home?utm_source=youtube&utm_medium=video&utm_campaign=lab-0024&utm_content=sponsor want to sponsor a future episode? [email protected] watch the full episode: https://youtu.be/eIGJmUUqUr8