Lenny’s AI Builders

Lennox Saint
  • 0.0 (0)
  • Entrepreneurship

less scrolling. more “oh shit, i could use that.” i’m Lennox. i dig through the AI updates worth your time, then test tools, models and agents on real work. what worked, what broke, and what you can try yourself. for people making products, content and useful systems with AI. you don’t need to write code to build something worth using. grab the field notes for prompts, steps and the bits to watch out for: https://lennoxsaint.com/lab this feed also keeps the earlier L E S S O N S episodes from my journey building with AI.

  1. 13h ago

    grok bot cut its limits. here's how to never run out mid-job | LAB 0036

    my grok bot agents hit 92% of the weekly limit and every new job just stopped. so i put one number on every agent: at 90%, stop new jobs, let what's running finish, and move anything urgent to codex. grok bot was sold as at least double the usage on the X subscription. then users watched their limits get cut (xAI hasn't published numbers), and elon said the cost of serving it was "unsustainably high relative to revenue". this episode is what i changed so my agents never run out mid-job - plus the one prompt i ran on my own roster, which showed i'm not using 322 of my 374 claude code skills. also in this episode: the upgraded siri opening to every app, claude plugins that log you into MCP servers, archon and remotion, 1,271 people affected at canva, and a model editing another model's weights. Threadify is my software for writing and scheduling Threads posts. it has a free 7-day trial: https://www.threadify.app/home?utm_source=podcast&utm_medium=audio&utm_campaign=lab-0036&utm_content=sponsor&video_slug=lab-0036&cta_slot=podcast_description&entry_angle=post_engine 0:00 grok bot cut its limits and my agents stopped at 92% 1:48 this is Lenny's AI Builders 2:03 the free lunch is over 2:30 the upgraded siri opens to every app 4:20 claude plugins now log you into their MCP servers 5:06 today's sponsor: Threadify 6:18 archon and remotion 7:21 canva: 1,271 people affected 9:16 a model edited another model's weights 10:13 oh sh*t, i could do that: put 90 on every agent 13:19 see you next time watch the full episode: https://youtu.be/mR8gmPlyj84

  2. 15h ago

    levelsio let Claude Code edit his whole vlog. i tried it on mine | LAB 0035

    levelsio said Claude Code edited his whole vlog from one line. so i ran the same line on my own raw footage. 25 minutes of working time, zero fixes from me, and a 10-minute vlog came out. a blind AI judge scored stills from it 6 out of 10. my real edit, with my own agents and about 10 rounds of notes, got 8 out of 10. the gap is direction. also in this episode: ChatGPT and Codex sharing one limit from December, Firecrawl's headless Clay for agents, your Claude subscription inside OpenCode, agent-desktop, a model editing another model's weights, and the improvements box Patrick Collison put in his apps - with the one prompt to build it yourself. Threadify is my software for writing and scheduling Threads posts. it has a free 7-day trial: https://www.threadify.app/home?utm_source=podcast&utm_medium=audio&utm_campaign=lab-0035&utm_content=sponsor&video_slug=lab-0035&cta_slot=podcast_description&entry_angle=post_engine 0:00 levelsio's one-line vlog edit, tested on my own footage 2:04 this is Lenny's AI Builders 2:20 why video editing is about to become a commodity 2:43 ChatGPT and Codex share one limit from December 4:50 Firecrawl: a headless Clay for agents 5:59 today's sponsor: Threadify 7:19 your Claude subscription works in OpenCode 8:39 agent-desktop: computer use for any coding agent 9:48 a model edited another model's weights 10:53 oh sh*t, i could do that: an improvements box for your app 13:36 see you next time watch the full episode: https://youtu.be/1ZTZYmSrOMU

  3. 1d ago

    Claude Ultra just removed the 5-hour limit. who should actually pay $200 | LAB 0034

    Claude Ultra just removed the 5-hour limit - but one line in the announcement says "weekly limits remain unchanged." so i put the new rule next to my own October lockouts: 22 limit messages, 16 separate walls. 10 were the 5-hour wall and 6 were weekly. only the 5-hour kind goes away, and only on the $200 Ultra plan. read your lockout message, find your wall, then pay for that one. also this week: a fake Claude Code extension in Cursor's store that left an SSH backdoor (and Cursor's one-line check), /REA-growth - reverse engineer any company's growth playbook for cents, Claude Code's hidden game rule, Sonnet 5 talking a researcher through mouse brain surgery after Opus said no, and Gemini 4 Carbon's first real test. thanks to today's sponsor, my software Threadify - your lead generation agent for Threads, X and YouTube. start your free 7-day trial: https://www.threadify.app/home?utm_source=podcast&utm_medium=audio&utm_campaign=lab-0034&utm_content=sponsor&video_slug=lab-0034&cta_slot=podcast_description&entry_angle=whats_working 0:00 Claude Ultra removed the 5-hour limit: my 22 lockouts 2:09 Anthropic's apology and the limits war 3:52 Lenny's AI Builders 4:09 fake Claude Code extension in Cursor 5:42 reverse engineer any growth playbook for cents 6:39 sponsor: Threadify 8:06 Claude Code's hidden game rule 9:12 Sonnet 5 talked him through mouse brain surgery 10:40 Gemini 4 Carbon gets a real test 11:37 the practical: reverse engineering Theo's T3 Code 13:58 see you next week watch the full episode: https://youtu.be/2JUxfjSK74c

  4. 1d ago

    openai just doubled codex limits. i checked what my plan is really worth | LAB 0033

    OpenAI just doubled Codex limits, so i ran one free command on my own account to see what my plan is really worth. at API list prices, my $500 a month plan did about $7,000 of work in the last 30 days - 14 times what i paid. then i put it next to Claude's $200 plan, and the gap made me rethink which plan i should be paying for. also this week: Kino and the "nobody can edit video with AI" fight (and why it took me six months), CLIProxyAPI - one proxy for all your AI accounts, Claude voice mode in Apple CarPlay, OpenAI's monitors catching a model reaching the internet through DNS during training, and Claude's API taking 128 MB requests. thanks to today's sponsor, my software Threadify - your lead generation agent for Threads, X and YouTube. start your free 7-day trial: https://www.threadify.app/home?utm_source=podcast&utm_medium=audio&utm_campaign=lab-0033&utm_content=sponsor&video_slug=lab-0033&cta_slot=podcast_description&entry_angle=lead_signal 0:00 OpenAI doubled Codex limits: what my $500 plan is really worth 1:42 Claude Max vs ChatGPT: which $200 plan wins 2:22 Lenny's AI Builders 2:39 "anyone claiming AI edits their videos is lying" 5:13 CLIProxyAPI: one proxy for all your AI accounts 6:38 sponsor: Threadify 7:50 Claude now works in Apple CarPlay 9:03 OpenAI's model reached the internet through DNS 9:33 Claude's API now takes 128 MB 10:34 the prompt: price your own AI plan 13:36 time-back: 9 missed calls, who to ring first 14:41 see you tomorrow watch the full episode: https://youtu.be/pc1RRp3ToXU

  5. 5d ago

    ChatGPT almost merged chat and work. i measured what actually eats your limit | LAB 0032

    one of my work chats used 2.51% of my weekly allowance. that was the whole automation chat, not one run. in this episode, i look at my usage page, the chat-and-work merge announcement and its walk-back as recorded on 29 october 2026. then i run 12 transcripts through the API and show the output, tokens and time. the credits shown in this recording don't cover Codex. check the terms and expiry on your own account before using them. the test took 16.83 seconds. the recorded list-price calculation was about seven cents - not a promise about your bill or current pricing. also in this episode: Gemini 4 Carbon, ChatGPT texts, reasoning effort, Claude for Legal, and what i still want the human to do when AI edits the video. Threadify is my software for writing and scheduling Threads posts: https://www.threadify.app/home?utm_source=podcast&utm_medium=audio&utm_campaign=lab-0032&utm_content=sponsor&video_slug=lab-0032&cta_slot=podcast_description&entry_angle=post_engine 0:00 one work chat and my weekly limit 0:20 my usage page 0:52 the API credits shown in my account 1:37 the merge announcement and walk-back 2:10 my take on the change 2:40 Lenny’s AI Builders 3:12 Gemini 4 Carbon 4:32 ChatGPT texts 5:32 sponsor: Threadify 6:31 reasoning effort 7:55 Claude for Legal 9:17 AI-run content 10:19 practical: 12 transcripts on API credits 12:36 see you next time watch the full episode: https://youtu.be/xK0tgeyWtmQ

  6. 5d ago

    they say ai video editing is solved. i tested it on my own launch video | LAB 0031

    i gave Opus 5.5, GPT-6.1 Terra and GPT-6 Astra my raw launch footage - retakes, word gaps, all of it - and one prompt: make me a short that i'd post. two finished in under three and a half minutes. one took 11. i watched all three side by side with no names, picked the one i'd post, then found out who made which. the times, the judge scores and what each edit cost are in the video. also this week: Artificial Analysis v5 (60% of it is now private tests or held-out answers), DeepSeek V4.1 Flash at 15 cents uncached in and 60 cents out per million tokens off-peak (and why cheap cuts both ways), ChatGPT now connects to iCloud mail and calendar, Grok Bot adds Apple access, Felix Rieseberg's tutorial behind my ambitious skill, and a lawsuit against OpenAI over GPT-4o (according to the lawsuit; OpenAI hasn't answered in court yet). the practical - five fake users break my site: five subagents, each a different first-time user, try my BuilderBench page in a real browser, then Claude fixes what they hit and reruns them. before: 33 issues and 1 of 5 users made it. after: 5 of 5. paste this into Claude Code in your own app's folder: Act as my launch QA lead. Spin up 5 subagents, each a different first-time user: 1. The impatient one: skims, clicks the first button, quits at the first error 2. The skeptic: reads pricing, terms and privacy before signing up 3. The mobile user: does everything on a 375px screen on slow 3G 4. The non-native English speaker: only follows what the UI literally says 5. The breaker: pastes junk into forms, hits back mid-flow, double-clicks everything Each one opens the app in a real browser, goes from landing page to first success, and screenshots every moment they get confused, stuck or annoyed. Merge everything into one list ranked by how many users hit it. Fix it all in one pass, then rerun the 5 users to prove it's fixed. Commit on a branch only. Don't push or deploy - i'll review first. time-back - the promises you didn't keep: paste two weeks of your texts, emails and voicemails into Claude with this prompt (swap in your own date, trade and sign-off). on sample data it found all 4 broken promises in 49 seconds and drafted a catch-up text for each. drafts only - you check them and send. Today is Wednesday 28 October 2026, 8am. I'm an electrician. Below are the last two weeks of my texts, emails and voicemails. Find every time I told someone I'd get back to them (a call, a quote, a refund, a time, an answer) and I haven't done it yet. Most urgent first. For each one tell me: who, what I promised, when I said I'd do it, how many days late it is, and why it's urgent. Then write one short catch-up text I can copy and send myself, owning the delay, with the actual answer or next step. Don't list promises I already kept, and tell me separately about any that are due today. Don't make anything up. Sign off as Marco, Westside Electrical. MESSAGES (paste your messages here) links BuilderBench (the page the five fake users tested): https://www.lennoxsaint.com/lab/builderbench Felix Rieseberg on being more ambitious with models: https://felixrieseberg.com/how-to-be-more-ambitious-a-tutorial-for-humans-with-models/ my ambitious skill, free on GitHub: https://github.com/lennoxsaint/Skills Artificial Analysis Intelligence Index v5: https://artificialanalysis.ai/articles/artificial-analysis-intelligence-index-v5 DeepSeek pricing: https://api-docs.deepseek.com/quick_start/pricing DeepSeek V4.1 Flash on the cyber rankings: https://alphasignal.ai/news/deepseek-s-v4-1-flash-1017-tops-public-cybersecurity-rankings-at-0-42-per-task ChatGPT + iCloud mail and calendar: https://9to5mac.com/2026/10/27/icloud-mail-and-calendar-plugins-now-work-with-chatgpt/ Grok Bot update: https://www.digitaltrends.com/phones/grok-bot-can-now-manage-your-calendar-reminders-and-more/ the GPT-4o lawsuit: https://techcrunch.com/2026/10/27/parents-sue-openai-alleging-gpt-4o-coached-their-daughter-off-seizure-medication/ chapters 0:00 three AI editors, one launch video 0:17 the edit-off: three phones, no names 1:16 the reveal: who made which 2:12 what each edit cost 2:28 taste is the human part 3:02 the computer-use irony 3:24 Lenny's AI Builders 3:49 Artificial Analysis v5 5:17 DeepSeek: cheap cuts both ways 6:23 sponsor: Threadify 7:25 iCloud connectors 8:21 Grok Bot 9:20 Felix's aside 9:49 the lawsuit: why human oversight matters 11:14 practical: five fake users break my site 13:18 time-back: the Greg Hollis text 14:10 see you tomorrow thanks to today's sponsor, my software Threadify - your lead generation agent for Threads, X and YouTube. it drafts posts from your own second brain, and my agents run it straight from Claude. start your free 7-day trial: https://www.threadify.app/home?utm_source=podcast&utm_medium=audio&utm_campaign=lab-0031&utm_content=sponsor&video_slug=lab-0031&cta_slot=podcast_description&entry_angle=post_engine want to sponsor a future episode? sponsors@lennysaibuilders.com watch the full episode: https://youtu.be/4T_aztz4ZCc

  7. 6d ago

    i let OpenAI's new Terra drive my computer. then Opus 5.5 got the same job | LAB 0030

    OpenAI just dropped GPT-6.1 Terra - a model that drives your computer, at half the price of GPT-6.1 Sol. so i let it do the admin in a made-up plumbing office on my computer: find the enquiry, book it in, write the quote. then i gave Opus 5.5 the exact same job, against the clock. both got it right, the faster one isn't the one i'd hire, and the price surprised me. also this week: Theo says the Claude Agent SDK drains your 5-hour limit faster than Claude Code (a GitHub issue a month ago measured about 1.8x per token, and Theo reports weekly limits aren't affected), OpenAI says its models proved three big results (nobody outside OpenAI has signed off yet), Anthropic filed to go public (revenue in the first half of 2026 was 14x the first half of 2025: $16.3 billion vs $1.2 billion), and AI video editing: CapCut's plugin for ChatGPT (announced), Instagram testing long horizontal videos, and Riverside's agents (live). the practical - BuilderBench, my own benchmark: GPT-6.1 Terra vs Kimi K3.1 Pro on 4 hours of real Threadify jobs, scored blind. one category wasn't even close. and a prompt that runs a mini blind test of any two models on one of your own jobs. save each model's answer in its own folder inside a folder called outputs, then paste this into Claude Code in the folder that holds outputs. the prompt: Make me a blind model test for my own work, like a mini BuilderBench. 1. Look in the folder ./outputs. Each subfolder is one model's work on the same job (the folder name is the model's name). 2. Copy each model's work into ./blind/ under a random label (Option A, Option B, ...). Save which label is which model in ./sealed/key.json. Don't show me the key and don't put model names anywhere in ./blind/. 3. Build one page, ./blind/score.html, that shows every option side by side (open HTML files in an iframe, show text files as text). Under each option: a score out of 10, one line "would I use this as is? yes / with fixes / no", and a notes box. 4. Add a "Lock my scores" button. Only after I lock, the page shows which model was which (read from a copy of the key that the page loads only after locking), the scores next to each name, and saves my scores to ./sealed/scores.json via a download. 5. Write ./blind/README.txt telling me how to open the page. Don't change anything in ./outputs. When you're done, tell me in 3 lines what you made. links GPT-6.1 Terra launch: https://x.com/OpenAI/status/2114780711664398349 GPT-6.1 Terra in Work and Codex (changelog): https://learn.chatgpt.com/docs/changelog OpenAI API pricing: https://developers.openai.com/api/docs/pricing Theo on the Agent SDK limits: https://x.com/theo/status/2114166439813017873 OpenAI's three results: https://x.com/gdb/status/2114837059462627533 Anthropic's S-1 on the SEC site: https://www.sec.gov/Archives/edgar/data/0002130357/000162828026067168/anthropicpbc-sx1.htm CapCut plugin for ChatGPT: https://x.com/capcutapp/status/2114062937094823955 Riverside Agents: https://riverside.com/blog/first-team-of-ai-agents-built-for-video the post on the end state: https://x.com/jsnnsa/status/2114566172163407964 chapters 0:00 Terra vs Opus 5.5: same admin job 0:19 the race, and who i'd hire 2:08 Lenny's AI Builders 2:47 the SDK limit bug (1.8x) 3:53 sponsor: Threadify 4:52 OpenAI's three results 6:08 Anthropic's S-1 (14x) 7:34 AI video editing agents 9:00 a look into the future 10:11 BuilderBench: Terra vs Kimi K3.1 Pro 11:49 the reveal 12:36 how the scores compare thanks to today's sponsor, my software Threadify - your lead generation agent for Threads, X and YouTube. it shows me which posts bring clicks and leads, and my agents run it for me straight from Claude. start your free 7-day trial: https://www.threadify.app/home?utm_source=youtube&utm_medium=video&utm_campaign=lab-0030&utm_content=sponsor&video_slug=lab-0030&cta_slot=youtube_description&entry_angle=whats_working want to sponsor a future episode? sponsors@lennysaibuilders.com watch the full episode: https://www.youtube.com/watch?v=B9N9mOY94Ww

  8. Oct 26

    Kimi K3.1 Pro just dropped - i made it race Opus 5.5 to build one game | LAB 0029

    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? sponsors@lennysaibuilders.com watch the full episode: https://www.youtube.com/watch?v=6LmucdqB0wU

See All (80)

About

less scrolling. more “oh shit, i could use that.” i’m Lennox. i dig through the AI updates worth your time, then test tools, models and agents on real work. what worked, what broke, and what you can try yourself. for people making products, content and useful systems with AI. you don’t need to write code to build something worth using. grab the field notes for prompts, steps and the bits to watch out for: https://lennoxsaint.com/lab this feed also keeps the earlier L E S S O N S episodes from my journey building with AI.

Information

  • Creator
    Lennox Saint
  • Years Active
    2026
  • Episodes
    80
  • Rating
    Explicit
  • Copyright
    © 2026 Lennox Saint
  • Show Website
    Lenny’s AI Builders