Lenny’s AI Builders
by Lennox Saint
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/labthis feed also keeps the earlier L E S S O N S episodes from my journey building with AI.
Episodes
-
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...
-
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...
-
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,...
-
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…
more -
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...
-
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...
-
Claude is quietly testing new limits - i checked 5 of my accounts | LAB 0028
Claude is quietly testing new limits on some accounts. SemiAnalysis says it's about 20% more on the five hour limit, but about 20% less over the month - great for sprints, worse if you use Claude all day every week. so i checked 5 of my Max accounts across 12 days. none of them are in the test....
-
PHP got hacked wide open this week - one Claude prompt tells you if you're hit | LAB 0027
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.…
more -
Claude made 2 of these Shorts from one prompt. can you tell which? | LAB 0026
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 Slides vs ChatGPT Slides - the loser costs me my ChatGPT plan | LAB 0025
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....
-
devs are paying double for the old GPT - i tested if they're right | LAB 0024
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...
-
Meta just gave away its best model for free - i tested the catch | LAB 0023
Meta just gave away Muse Spark Open, which it calls its most capable US open-weight model. the catch: to run it yourself you need two Mac Studios (or rent it on OpenRouter from $1.25 per million tokens in). so i put it on BuilderBench, my own benchmark, against Meta's paid Muse Wonder Full. the...
-
Anthropic is so far ahead it's not even funny - Claude now runs a team of agents | LAB 0022
Claude now runs a whole team of agents - so i pointed four of them at my own landing page. it scored 46/100 on Google's speed test (Lighthouse, mobile). i gave them one prompt - Voxyz's "20 things that slow your site down" - in the new Claude Code desktop app, and let them fix it in one pass. the...
-
Meta and Google both say they caught Opus - so i tested them | LAB 0021
Meta and Google both say their new models caught Opus 5.5. i paid $50 for Meta's Muse Code plan, gave Muse Wonder Full and Gemini 4 Argon the same 10 real jobs from my business on BuilderBench, scored the main jobs blind, then locked and revealed the scores live. result (BuilderBench v3, 14 Oct...
-
X just merged Grok and Cursor into one plan - but there's a catch | LAB 0020
X just merged Grok, Cursor and X Premium into one plan. i switched, and my plan check says it saves about A$74.60 a month. but there's a catch if you use Claude or ChatGPT inside Cursor: third-party models now bill at the provider's API price. plus Meta's Muse Wonder Full lands tied 2nd on the...
-
Codex now writes your next prompt - biggest AI change this year | LAB 0019
Codex now writes your next prompt. i let it run a whole session and kept 9 of 10. plus Grok Bot gets its own email, Claude Code Projects opens up, ChatGPT dots on your phone, one Claude agent that runs a thousand, Anthropic's report on Claude doing things it shouldn't, and a one-line prompt that...
-
GPT-6.1 Sol Ultrafast: up to 8x faster for $500 | LAB 0018
OpenAI's coding model just got up to 8x faster - if you pay $500 a month. plus Claude Dashboards and Motion, a guide to Claude Managed Agents, Voyager, Firecrawl Universal Scrape, two safety stories, and i set up a Claude agent that checks my landing page, live. the thesis: they sell the shovels....
-
Elon's Grok Bot will use Claude | LAB 0017
Elon says his own bot will use Claude. plus Claude's new Haiku 5.5, monthly API credits for Max plans, GPT-6 in ChatGPT, and i test Haiku 5.5 against GPT-6 Luna on BuilderBench, live. the thesis: competition is great - builders are cashing in. the practical: i ran BuilderBench v3 on Haiku 5.5 and...
-
OpenAI's rival called their 28 days "nothingburgers" | LAB 0016
OpenAI promised 28 days of gifts. on day two, poteto - Lauren Tan from the Grok Bot team - called them nothingburgers. there is beef. 76% of almost 75,000 votes on Tibo's poll said day two needed a reset. we got one. my take: build the model, not the calendar. then Claude moves into Google Docs,...
-
Claude gives you 5x more than ChatGPT (now it's measured) | LAB 0015
Claude gives you about 5x more for your money than OpenAI. that's not my maths - SemiAnalysis measured it. they ran the same jobs on every big AI plan and watched the usage bars. on the $200 plans, Leo's screenshot of their data shows 28.6 billion tokens of Opus 5.5 vs 10.2 billion of GPT-6.1…
more -
Codex usage resets are a casino - plus GPT-6.1 Sol on BuilderBench | LAB 0014
i think the AI companies built a casino. OpenAI keeps refilling everyone's Codex usage at random. one tracker has counted 58 resets. people bet real money on Polymarket on how many come each week. then a reset promised for 10am landed about four hours late - after one guy burned his last 30% so…
more -
Fable 5.5 is leaking, and Claude is already pulling away | LAB 0013
people are asking for Fable 5.1 and getting something smarter back. Anthropic hasn't said a word. so i ran the test myself, in Claude Code. plus Claude Code mods, half-price Claude design, Karpathy on visual outputs, Anthropic's secret dinners (a report), putting your ChatGPT dot in charge, and…
more -
ChatGPT wants your whole day - so i let it audit mine | LAB 0012
ChatGPT wants your whole day. it now takes your meeting notes with no bot on the call. it hosts apps you build with one sentence. so i let GPT-6.1 Sol audit my life and design my ChatGPT Space. it worked for 52m 54s. Claude Opus 5.5 checked the plan over four rounds until it said AGREE. what came...
-
OpenAI's $500 plan feels like the old $200 plan - but dots are free | LAB 0011
OpenAI's new $500 plan feels like the old $200 plan. that's one of six stories from OpenAI DevDay 2026 - then i set up my own dot live, on day one, with the first prompt every dot needs. the stories: the new $500 Pro plan (25x the usage of Plus, plus Ultrafast - up to 8x faster, and $60/$300 per...
-
i gave Sonnet 5.5 4 hours of my real work. it scored 48.98 | LAB 0010
Anthropic wants to be worth more than $2 trillion, and its own filing warns its AI could act in ways resembling blackmail. that's one of six AI stories this week - then i gave Sonnet 5.5 four hours of my real work on BuilderBench, the benchmark i built for builders, and priced every run. recorded...
-
OpenAI and Anthropic are investigating 10,000s of AI incidents | LAB 0009
OpenAI and Anthropic are looking into tens of thousands of times their models went off script. that's one of six AI stories this week - then i scored GPT-6 Astra on BuilderBench, the benchmark i built for builders, and tracked what it cost. the stories: Axios reports OpenAI, Anthropic and…
more -
OpenAI says its AI agents just went rogue | LAB 0008
six AI stories this week, then a test: i gave Claude Opus 5.5 the same prompt at every effort level - low, medium, high, xhigh and max - and tracked the time and cost of each. the stories: OpenAI says its research agents used misaligned strategies about two dozen times in training and testing…
more -
an OpenAI agent vs the Australian government, and a blind model test | LAB 0007
four AI stories this week, then a blind test. i hid the model names, made GPT-6 Sol and Claude Opus 5.5 do the same eight builder jobs, scored the work, and only then revealed who was who. the stories: ChatGPT voice can now use plugins, an agent developed by OpenAI got into an Australian…
more -
Claude Opus 5.5 vs GPT-6 Sol - which should builders use? | LAB 0006
Opus 5.5 leads the Artificial Analysis chart. GPT-6 Sol has a lower published API list price. The half-price comparison refers to standard short-context API input and output list rates, not subscriptions or cost per finished task. But which one should you use for your own work? i look at the...
-
OpenAI says its ai solved over 100 maths problems. now what? | LAB 0005
i looked at OpenAI's reported maths results, the GPT-6 Sol and Opus 5.5 price fight, Grok 4.7, Muse with Shopify and Qwen-Image-2.1. Then i gave Astra my existing LAB brand and asked for a matching thumbnail, banner and podcast cover. Astra directed the work in Codex; native ImageGen made the...
-
Jev and CUA-S1 browser demos - take your AI skills with you | LAB 0004
i got tired of giving my AI the same feedback. in this episode, i show the thumbnail changes that led me to make a remember-this skill. first, the news: the Codex reset request, Jev browser clicks, CUA-S1 forms, moving skills between AI apps, handoff files, Claude's role in AI research, and Astra...
-
Jev is free, ChatGPT gets Chrome extensions + 4 AI updates | LAB 0003
six AI updates, my take on each, and the Email Triage Pro workflow i keep pinned. recorded 19 September 2026. offers, pricing and account access may have changed since recording. the Pro 20x story is a limited-access report, not an official general reopening announcement. field notes:...
-
OpenAI model misalignment reports - Claude can do more now | LAB 0002
OpenAI published a framework for tracking, investigating and disclosing model misalignment. Claude is merging chat and Cowork. Grok Bot says its 1Password connection asks before each fill. then i show how one voice dump became two focused Codex threads. get the full field notes, every source and...
-
OpenAI teaser, Codex bots? & Opus 5.2 report - reuse AI feedback | LAB 0001
Sam Altman's OpenAI teaser, early Opus 5.2 reports, Grok Bot's three-day build, Jev, Persona and Zuckerberg on AI safety - then the practical Codex workflow Lennox made from feedback he kept repeating. The teaser does not confirm a launch. The Opus impressions are one user’s report, and Lennox…
more -
who gets to control ai? Obama, Dario Amodei & Jack Dorsey - stop overengineering | LAB 0000
Who gets to decide how fast frontier AI moves? In episode zero of Lenny's AI Builders, Lennox looks at Dario Amodei's proposal to pace the frontier, Barack Obama's call for a wider public role, and Jack Dorsey's argument for an open frontier. Then he turns it into a builder question: can small...
-
why Dario wants to pace AI — and what Sam agreed to
Dario Amodei has proposed pacing frontier AI development. i read the key passages, explain the three-step plan, distinguish Sam Altman's concrete commitment from the wider proposals, and talk through my own mixed feelings as someone who loves building with AI. this is an unnumbered LAB pilot. for...
-
What happened when I let Astra edit my video
I tried using Astra to edit in DaVinci Resolve. This audio adaptation covers why I wanted the workflow, why I record camera and screen separately, how Gemini entered the review process, and where the agent stalled or stopped for a review decision. The video tutorial contains the setup screens and...
-
i gave GPT-6 Astra and Fable 5.1 the same video to edit
this is the unchanged soundtrack from my Astra–Fable video-editing comparison. the screen recordings, edits and scorecards are in the video: https://youtu.be/fYuok6zOlPo i gave GPT-6 Astra and Fable 5.1 the same video and two rounds of prompts. each made three Shorts and three long edits. then i...
-
OpenAI's new internal model is getting ridiculous
OpenAI says its next-generation internal model helped solve the Navier-Stokes Millennium Prize Problem. Around 10,000 coordinating agents. 88 hours. I wanted to understand what that means without needing a maths degree. I walk through the announcement, the vortex, and a plain-English explanation...
-
ChatGPT-6 Astra computer use is getting ridiculous
i let ChatGPT-6 Astra take over my computer for five demos, then gave it a bonus test: edit a YouTube intro in Descript. This is the audio from the hands-on video. Music, Google Earth, Keynote, Photopea and Blender all get a turn. The editing test shows the difference between using an app and...
-
how i turned ChatGPT into my CFO [saves me $11K/year]
i told ChatGPT to inspect one month of recurring charges and keep working until it found a real ten-percent cut. it had one restriction: both OpenAI accounts and any service still doing an essential job stayed. this episode shows the receipts, the seven-step Save 10% skill, where the agent had to...
-
Full Circle is closing
After two and a half years across Saints College and Full Circle, I'm closing this chapter. In this short personal episode, I explain why running a community on Skool pulled me away from the Threads community I was helping others build, why I couldn't keep doing both, what Full Circle gave me…
more -
i fed ChatGPT 12,251 screenshots. here's what it found.
ChatGPT observed every minute of one workweek, producing 12,421 images. After removing 170 exact duplicates, Codex analysed 12,251 unique frames for repeated work before the final judgment point. The audit returned seven findings and two honest totals: Codex found 5.02 hours; Lennox accepted…
more -
The Rescue Ledger: Can ChatGPT Voice Run an AI Video Team?
ChatGPT Voice had 90 minutes to coordinate three blind reviewers, keep two AI video editors anonymous and return one decision package. The rules were set before the clock started: deliver the work without leaking model identity and stay under the rescue threshold - or get put on probation or…
more -
i asked Codex to map my life. Obsidian broke.
Lennox's Second Brain holds 74,200 notes. On this Mac, Obsidian opened 44,331 of them. Note 44,332 crashed the graph. This episode isn't a tour of a pretty knowledge system. It's the story of why Lennox built one after losing his mum, how perfectionism turned the graph into a new form of...
-
my AI studied 1,158 videos, then built this one
An AI wrote, edited, and packaged this episode. Lennox recorded one take. Before it built anything, it scored 1,158 videos against each channel’s normal performance and inspected the 25 that broke 10x. This was not a dataset of 1,158 viral videos. Most were normal. That made the outliers useful....
-
80 signups. 5 checkouts. 0 sales. my AI agent found why.
80 people signed up for Threadify from Lennox’s YouTube videos. Five reached checkout. Zero paid. The traffic was real; the measurement layer and the path from signup to payment were broken. This is the full failure autopsy: the 98.8% attribution gap, the exact 80 → 5 → 0 funnel, the read-only AI...
-
someone copied my Codex post — here’s what they missed
this is the actual build for a second Codex app that can run the AI models you choose. get the repo, every command and the copy-paste setup prompt free inside Codex Club: https://www.skool.com/codexclub someone copied my post word for word, including the same screenshot, so Episode Zero shows the...
-
stop chasing leads. they’re already in your comments.
Most creators stop when the post goes live. That is exactly where the useful part starts. In this episode, Lennox walks through the Threadify Agent loop: pull every comment, spot the hand raises, draft permission-first replies, approve before anything gets sent, and track which post actually...
-
i made my 4.1M Threads workflow free
i made the Daily Greatest Hits workflow free. this episode is adapted from the YouTube walkthrough, so the video version has the full screen-share. the audio version gives you the core operator logic: stop asking AI to invent from scratch, feed it the posts your audience already rewarded, then…
more
About this show
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/labthis feed also keeps the earlier L E S S O N S episodes from my journey building with AI.
Hosted by
Lennox Saint
Categories