Lenny’s AI Builders

Grok Bot 1.0 isn't new. the bot has been out since August, and xAI's own page calls 1.0 a major update to its AI teammates. the headline feature, team bots, is for Team and Enterprise plans. so if you're solo, you got a number, not really an upgrade. the upgrade that actually matters is the quiet one: Grok Bot can now join your Tailscale network. i put my bot on my private network, where four read-only doors lead into my Mac. that morning it counted 42 active agent tasks and listed my four local models in 3 minutes 27 seconds. one read out of four timed out twice. then i ran it again live at 1:38 and it failed on camera. i left that in. also in this episode: Gemini 4 Carbon's score on my own benchmark, BuilderBench, revealed live (3:16). Fable 5.2 takes number one in Agent Arena (30.4% net improvement at $7.32 a task, against 19.5% and $5.33 for Opus 5.5 - Arena doesn't define "net improvement" on the pages i read). Gemini Decision 1, a model that only picks an answer off a list (2 to 255 choices, $0.10 per million input tokens, output free). the GPT-6.2 rumour, which was still a rumour when i filmed. and Nvidia's board and Jensen Huang. update since filming: on November 12 Nvidia announced that Jensen Huang resigned as CEO, and CFO Colette Kress is interim CEO. when i filmed, it was still a report. Threadify is my lead generation agent for Threads, X and YouTube. one of my posts got more replies than i could read, so i had Threadify show me the ones that matter most. free 7-day trial, card required: https://www.threadify.app/home?utm_source=podcast&utm_medium=audio&utm_campaign=lab-0042&utm_content=sponsor&video_slug=lab-0042&cta_slot=podcast_description&entry_angle=lead_signal want to sponsor a future episode? [email protected] 0:00 Grok Bot 1.0 isn't new 0:43 so what is 1.0? 1:14 the real upgrade: Tailscale and four doors 1:38 the live re-run (it failed) 2:37 this is the LAB 2:57 today's question: does it beat Opus 5.5? 3:16 Gemini 4 Carbon on BuilderBench: the reveal 5:35 Fable 5.2 takes number one in Agent Arena 6:42 today's sponsor: Threadify 7:43 Gemini Decision 1 8:55 the GPT-6.2 rumour 9:49 Nvidia's board and Jensen 10:47 the practical: the finishing work paragraph 12:17 so, does it beat Opus 5.5? watch the full episode: https://youtu.be/JelRGipwZ_Y

i ran one Claude Fable 5.2 conductor on my real app, Eddy Studio, for 40 hours. it messaged 73 worker threads, and 25 merged pull requests link back to the run. my weekly Fable limit was gone in 13 hours. the new meta: Fable 5.2 costs twice what Opus 5.5 does, so Fable directs the show and Opus does the work. the practical, four steps: open Claude Code, type /model and pick Fable 5.2, set your sub-agents to Opus 5.5, then give it a massive job and add the conductor paragraph. start with three workers, not 73. the paragraph and the full skill: https://github.com/lennoxsaint/Skills also this episode: Gemini 4 Carbon, Claude Sheets, Data and Whiteboards, Anthropic's free full reset, Businesses in ChatGPT and what its terms say, and Anthropic's IPO filing with the Astra rumour (one account's post - a rumour). Threadify is my lead generation agent for Threads, X and YouTube. connect the Threadify MCP to Claude and it manages my posting schedule, picks the best time for me to post and shows me the most important replies i need to answer. free 7-day trial: https://www.threadify.app/home?utm_source=podcast&utm_medium=audio&utm_campaign=lab-0041&utm_content=sponsor&video_slug=lab-0041&cta_slot=podcast_description&entry_angle=agent_mcp 0:00 i ran one Fable 5.2 conductor for 40 hours 0:16 what it actually built 0:59 the conductor paragraph, word for word 1:41 the stats and the mess 2:38 the new meta: Fable directs, Opus works 3:18 this is the LAB 3:41 the thread: Anthropic's aura is not a coincidence 4:00 Gemini 4 Carbon 5:08 Claude Sheets, Data and Whiteboards 7:05 today's sponsor: Threadify 7:52 the free full reset 9:13 Businesses in ChatGPT 11:01 Anthropic's IPO and the Astra rumour 12:59 the practical: four steps watch the full episode: https://youtu.be/yw5yOAV3KPI

Claude Fable 5.2 just dropped, and there's only one job i'd actually pay it for: the boss. it reads the task, picks which worker gets it and knows when the output is good. Opus 5.5 does the hours. so i ran Fable 5.2 blind against Opus 5.5 on 10 kinds of my real work, on my own benchmark, BuilderBench. i made my bet before i saw a score. the result is at 10:35. the practical: in Claude Code, run /model fable for the main chat, then set your subagents to opus. also this week: Fable resets and the catch, Grok Bot resetting weekly limits, OpenAI's dot running on several of your computers, Meta's Muse Ember, and the Jensen Huang, Nvidia and Megaspeed story (reported by the FT and the NYT, Nvidia says it was investigated and debunked, nothing proven). Threadify is my lead generation agent for Threads, X and YouTube. it reads the replies on your posts and flags the people showing real buying signal, so you spend your attention where it counts, and nothing goes out until you say yes. free 7-day trial: https://www.threadify.app/home?utm_source=podcast&utm_medium=audio&utm_campaign=lab-0040&utm_content=sponsor&video_slug=lab-0040&cta_slot=podcast_description&entry_angle=lead_signal 0:00 the one job i'd pay Fable 5.2 for 0:19 Fable 5.2 is the boss, Opus 5.5 the workers 3:01 this is the LAB 3:17 the thread: AI just got a pay scale 3:50 Fable resets have a catch 5:22 Grok Bot resets weekly limits 6:22 today's sponsor: Threadify 7:06 OpenAI's dot runs on several of your computers 8:19 Meta's Muse Ember 9:38 Jensen Huang, Nvidia and the Megaspeed story 10:35 the bench: Fable 5.2 vs Opus 5.5, blind 12:37 the catch + outro watch the full episode: https://youtu.be/rqeKU4Fr_pQ

i let claude dream over my agents' memory. i gave it six months of my own agent logs, then checked every change it made against my real log. my agent's notes went from 7 to 9 out of 10 on a quiz i wrote before the run. of 125 edits, 54 held up, 58 held up only partly, 2 did not hold up, and 11 had no log day to check. the catch: this is my own version of dreaming, not anthropic's feature (i don't have access yet). it was one run, 10 questions, and claude graded its own homework. so read 7 to 9 as a sketch of the idea, not a benchmark. the practical: tell your agent to read its own notes and logs between jobs, then ask what's wrong and what it can do better. that is all dreaming is. also this week: Claude Code cloud sessions, Claude Duet, Grok Bot joining meetings, Meta's Muse Wonder memory, and Nous Research's Arete-27B. Threadify is my lead generation agent for Threads, X and YouTube. it remembers how you write, drafts your posts, threads and replies so they already sound like you, and nothing goes out until you say yes. free 7-day trial: https://www.threadify.app/home?utm_source=podcast&utm_medium=audio&utm_campaign=lab-0039&utm_content=sponsor&video_slug=lab-0039&cta_slot=podcast_description&entry_angle=voice_brain 0:00 i let claude dream over my agent's memory 0:15 what happened: dreaming on six months of my logs 1:31 what anthropic actually reports 2:48 why this matters 3:51 the thesis: memory makes agents useful 4:10 Claude Code cloud sessions 5:17 Claude Duet 6:28 today's sponsor: Threadify 7:29 Grok Bot joins meetings 8:43 Meta's Muse Wonder memory 10:05 Nous Arete-27B 11:27 the practical: dream over your agent's notes 12:38 wrap-up watch the full episode: https://youtu.be/4goanD5lGAo

i tested the Claude Code skill that reverse-engineers any viral video. i fed it my best edit and checked every cut it found against my real edit file. in the first minute it found 7 of my 14 jump cuts, and 15 of the 17 cuts it flagged were real. over the whole 14 minutes it caught about 1 in 3. the catch: the full reverse skill needs HyperFrames Pro ($25 a month), and it can tell you what i did, not why people watched. that gap is the one thing it can't see - stick around, i show you what it is at the end. the practical: i ran Cloudflare's free security audit skill on my own Mac app, Eddy Studio. read-only, about 23 minutes. 0 confirmed, 3 leads to test, 2 ruled out. it only read the code, so zero confirmed means not proven yet - not safe. also in this episode: Claude Personal Finance (US beta, read-only) and Pompliano's story, Cursor building live apps you can share with a link, Perplexity Teammates, and METR on AI speeding up AI research about 2x. Threadify is my lead generation agent for Threads, X and YouTube. it drafts your posts, threads and replies so they already sound like you, schedules them at your best time, and nothing goes out until you say yes. free 7-day trial: https://www.threadify.app/home?utm_source=podcast&utm_medium=audio&utm_campaign=lab-0038&utm_content=sponsor&video_slug=lab-0038&cta_slot=podcast_description&entry_angle=post_engine 0:00 i tested the skill that reverse-engineers any viral video 0:12 7 of 14 cuts found 2:13 this is Lenny's AI Builders 2:28 AI can now pull apart anything that works 2:49 Claude Personal Finance 4:35 Cursor builds live apps 5:46 today's sponsor: Threadify 7:02 Perplexity Teammates 7:58 Cloudflare's free security audit skill 9:14 METR: AI speeds up AI research about 2x 10:26 the practical: a free security audit on my own app 11:37 the one thing it can't see watch the full episode: https://youtu.be/1YF5B9dOPAs

Grok Bot can now make phone calls. so i asked it to ring a hotel in New York and haggle the price. it showed the call card, said it was dialing the New Yorker... then blocked. the call was never even dialed. the catch: Grok Bot can only make calls while you're in the US. if you're not, there's no working around it. when it does work, you just ask in chat - it rings the number, talks to a person and tells you what happened. one early user on X said an 85-second call moved his usage from 5.8% to 6.0% (his plan isn't known, so take it with a pinch of salt). the practical: i told Claude to save a memory to Notion Memories, then asked ChatGPT to read it back. it worked - ChatGPT found the memory and listed its four rules. but Notion labelled it "created by ChatGPT", even though Claude wrote it. the trick is to be explicit: tell your agent "add this to Notion Memories" or "check my Notion Memories". also in this episode: Claude Code background sub-agents now use less of your limit, Notion's one shared brain for your agents, ChatGPT Images 2.6 (plus an AI Lenny test), Kimi K3.1 Pro open weights and what it would take to run them on Macs, and Cat Wu leaving Claude Code for OpenAI. Threadify is my lead generation agent for Threads, X and YouTube. it drafts your posts, threads and replies so they already sound like you, and nothing goes out until you say yes. free 7-day trial: https://www.threadify.app/home?utm_source=podcast&utm_medium=audio&utm_campaign=lab-0037&utm_content=sponsor&video_slug=lab-0037&cta_slot=podcast_description&entry_angle=voice_brain 0:00 Grok Bot can make phone calls now. mine was blocked 2:15 this is Lenny's AI Builders 2:30 AI just walked out of the chat box 2:56 Claude Code background sub-agents now use less of your limit 4:14 Notion gives your agents one shared brain 6:13 today's sponsor: Threadify 6:59 ChatGPT Images 2.6, and an AI Lenny test 8:23 Kimi K3.1 Pro open weights 9:38 Cat Wu leaves Claude Code for OpenAI 11:10 the practical: one Notion brain, Claude and ChatGPT 14:19 see you next time watch the full episode: https://youtu.be/4S05I4s0-I0

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

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

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

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