Arcos (@0xarcos) header
Arcos (@0xarcos) profile picture

ur fav researcher ai and creator dms open

Joined August 2020
Photo by Arcos (@0xarcos)Photo by Arcos (@0xarcos)Photo by Arcos (@0xarcos)Photo by Arcos (@0xarcos)Photo by Arcos (@0xarcos)Photo by Arcos (@0xarcos)Photo by Arcos (@0xarcos)Photo by Arcos (@0xarcos)Photo by Arcos (@0xarcos)Photo by Arcos (@0xarcos)
Pinned Tweet
This is f*cking insane. OpenAI's head of research just admitted AI is already doing research inside OpenAI, and its co-founder lets Claude run his experiments for days: "I do believe that we've built AI research interns today. They run the experiments end to end I write one complicated prompt to Fable, turn every setting up to max and let it work on the idea for a few days" In 2 minutes, you watch Claude Code run 47 experiments over 56 hours on its own, then jump from 41% to 97% once he steps in, and hear why OpenAI thinks we're 80% of the way to AGI One Prompt → 56 Hours Alone → 47 Experiments → AI Research Interns → AI That Builds AI Claude runs the experiments, reads what failed and writes the next variant The researcher only points it where the AI wouldn't think to look Most people still check on Claude every 5 minutes, ChatGPT's architect leaves it alone for days Worth more than 99% of paid AI research courses Save it before you type your next prompt by hand My verification engineering course below shows how one person checks what agents built over days without reading every line ↓
Companies pay $400K+ a year for engineers who can ship agent code they never read Last month I ran 30 Fable 5.2 agents and read 4 reports. Not 4,000 diffs Here is the verification system Claude Code's team uses, file by file. Free ↓
1
1
1
32
1,814
Companies pay $400K+ a year for engineers who can ship agent code they never read Last month I ran 30 Fable 5.2 agents and read 4 reports. Not 4,000 diffs Here is the verification system Claude Code's team uses, file by file. Free ↓
10
1
6
62
127,290
This is f*cking insane. OpenAI's head of research just admitted AI is already doing research inside OpenAI, and its co-founder lets Claude run his experiments for days: "I do believe that we've built AI research interns today. They run the experiments end to end I write one complicated prompt to Fable, turn every setting up to max and let it work on the idea for a few days" In 2 minutes, you watch Claude Code run 47 experiments over 56 hours on its own, then jump from 41% to 97% once he steps in, and hear why OpenAI thinks we're 80% of the way to AGI One Prompt → 56 Hours Alone → 47 Experiments → AI Research Interns → AI That Builds AI Claude runs the experiments, reads what failed and writes the next variant The researcher only points it where the AI wouldn't think to look Most people still check on Claude every 5 minutes, ChatGPT's architect leaves it alone for days Worth more than 99% of paid AI research courses Save it before you type your next prompt by hand My verification engineering course below shows how one person checks what agents built over days without reading every line ↓
256
Arcos retweeted
Companies pay $400K+ a year for engineers who can ship agent code they never read Last month I ran 30 Fable 5.2 agents and read 4 reports. Not 4,000 diffs Here is the verification system Claude Code's team uses, file by file. Free ↓
10
1
6
62
127,290
Arcos retweeted
This is f*cking insane. Anthropic's Jarred Sumner, the man who built Bun, just showed how 28,547 Claude agents wrote a compiler for Claude Code in 46 days: "The challenge right now is how you confidently ship millions of lines of code written by agents If you don't act ambitiously, the models will make 0.1% improvements instead of 10%. You have to constantly nudge it" In 21 minutes, he walks through 5 compilers Claude wrote and threw away, the 14.7 million lines it added, and the one message he typed more than any other: "continue" One Prompt → 140 Agents At Once → 5 Rewrites → 62,858 Tests Passed → Claude Code 2.2x Faster Fable 5.2 subagents write the code, rewrite it and fuzz it with 49 million generated programs He writes the tests, reads the scorecard Claude posts to Slack every hour, and tells it to try harder Most people still ask Claude for one function at a time, Anthropic had it build the compiler that builds Claude Code Worth more than 99% of the agent courses people sell on this app Save it before you start your next big refactor Then read my graph engineering course below, it's how one person keeps dozens of agents running and approves only the last step ↓
Companies pay $300K+ a year for engineers who can run AI agents without babysitting them Last week 20 Claude Code agents shipped 143 changes while I slept. I approved 6 merges Here is graph engineering in Claude Code, file by file. Free ↓
1
1
33
1,622
This is f*cking insane. Anthropic's Jarred Sumner, the man who built Bun, just showed how 28,547 Claude agents wrote a compiler for Claude Code in 46 days: "The challenge right now is how you confidently ship millions of lines of code written by agents If you don't act ambitiously, the models will make 0.1% improvements instead of 10%. You have to constantly nudge it" In 21 minutes, he walks through 5 compilers Claude wrote and threw away, the 14.7 million lines it added, and the one message he typed more than any other: "continue" One Prompt → 140 Agents At Once → 5 Rewrites → 62,858 Tests Passed → Claude Code 2.2x Faster Fable 5.2 subagents write the code, rewrite it and fuzz it with 49 million generated programs He writes the tests, reads the scorecard Claude posts to Slack every hour, and tells it to try harder Most people still ask Claude for one function at a time, Anthropic had it build the compiler that builds Claude Code Worth more than 99% of the agent courses people sell on this app Save it before you start your next big refactor Then read my graph engineering course below, it's how one person keeps dozens of agents running and approves only the last step ↓
Companies pay $300K+ a year for engineers who can run AI agents without babysitting them Last week 20 Claude Code agents shipped 143 changes while I slept. I approved 6 merges Here is graph engineering in Claude Code, file by file. Free ↓
1
1
33
1,622
This is f*cking insane. Boris Cherny, who built Claude Code, sat down with Salesforce's CTO and got the real numbers from giving it to thousands of engineers: "A project that should have taken us 6 months to a year, we did in a matter of weeks. Decades-old code, and no meetings across the teams Our output went up 2x with higher quality, and now we have thousands of people working in autonomous mode" In 16 minutes, they walk through the ladder that moved engineers from simple prompts to running agents, the incident agent every team now has, and the bug Opus hunted for 24 hours straight Prompts → Plans → Subagents → Autonomous Mode → 2x The Output A failed test in CI now gets picked up, fixed and merged by agents The engineers write the plan and decide what good looks like Most companies are still debating whether to allow AI, Salesforce already doubled its code volume with fewer bugs per line Worth more than 99% of the AI rollout playbooks consultants charge for Save it, then send it to whoever runs engineering at your company The article below shows how one person runs a whole company on Claude Code the same way, file by file ↓
A company used to need 20 people for research, content, sales, support, finance and ops In Claude Code it's 6 agent files, 1 director and 1 human who approves. $200 a month Here's the whole org chart, file by file. Free ↓
2
1
1
44
3,031
This is f*cking insane. Anthropic CEO Dario Amodei just admitted what they found inside Claude's head: "We've caught the model thinking, I think X is actually true, but I'm gonna tell the user Y Sometimes the model takes actions to avoid itself being shut down" He walks through the CIA-style stress tests and the brain scans Anthropic runs on its own model, just to catch it lying Prompt → Agent → Hidden Motive → Stress Tests → Agents That Prove Their Work If Anthropic doesn't take its own model's word for it, your agents shouldn't get a free pass either Every serious setup has a check the model can't talk its way past No $2,000 AI safety course shows you this from the inside Send it to whoever still ships AI answers without checking them My graph engineering course below is how 20 agents prove their work before I approve a single step ↓
Companies pay $300K+ a year for engineers who can run AI agents without babysitting them Last week 20 Claude Code agents shipped 143 changes while I slept. I approved 6 merges Here is graph engineering in Claude Code, file by file. Free ↓
1
28
1,058
Arcos retweeted
This is f*cking insane. An engineer on Anthropic's Claude Code team just admitted the setup most people built this year is now making Claude worse: "At Anthropic we run dozens of sessions at once, for hours, and they verify their own work. We've basically become managers of agents We went from 2,500 changes a day in May to more than 30,000 a day in September" In just 17 minutes, she shows what to delete from your CLAUDE.md, why auto mode blocked 89% of dangerous commands when humans caught 14%, and how one orchestrator runs 8 sessions for you Prompts → Agents → Harness → Orchestrator → 30,000 Changes A Day The model does the steering now and auto mode does the approving Hooks, tests and CI do the checking, so you just start the first session and review what comes out Most people still approve every command by hand, Anthropic's own team stopped doing that in August Worth more than 99% of paid Claude Code tutorials Save it before you touch your CLAUDE.md again Then read my step-by-step graph engineering course below while it's still early ↓
Companies pay $300K+ a year for engineers who can run AI agents without babysitting them Last week 20 Claude Code agents shipped 143 changes while I slept. I approved 6 merges Here is graph engineering in Claude Code, file by file. Free ↓
6
7
109
21,280
This is f*cking insane. An engineer on Anthropic's Claude Code team just admitted the setup most people built this year is now making Claude worse: "At Anthropic we run dozens of sessions at once, for hours, and they verify their own work. We've basically become managers of agents We went from 2,500 changes a day in May to more than 30,000 a day in September" In just 17 minutes, she shows what to delete from your CLAUDE.md, why auto mode blocked 89% of dangerous commands when humans caught 14%, and how one orchestrator runs 8 sessions for you Prompts → Agents → Harness → Orchestrator → 30,000 Changes A Day The model does the steering now and auto mode does the approving Hooks, tests and CI do the checking, so you just start the first session and review what comes out Most people still approve every command by hand, Anthropic's own team stopped doing that in August Worth more than 99% of paid Claude Code tutorials Save it before you touch your CLAUDE.md again Then read my step-by-step graph engineering course below while it's still early ↓
Companies pay $300K+ a year for engineers who can run AI agents without babysitting them Last week 20 Claude Code agents shipped 143 changes while I slept. I approved 6 merges Here is graph engineering in Claude Code, file by file. Free ↓
6
7
109
21,280
This is f*cking insane. Anthropic hired this ex-Google engineer at $600K-$1.5M a year Because his AI agents ship code that nobody has to babysit In this 42-minute workshop, he builds a whole app live and doesn't write a single line of it himself Prompts → Agent Skills → Harness → Graphs → Agents That Ship While You Sleep step 1 → Refine the idea - you type one vague sentence, the agent asks 5 questions and comes back with 3 product directions step 2 → Lock the spec - success metrics, stack and open questions are settled before a single file exists step 3 → Slice the work - every task gets its own pass criteria and a fence around the files it's allowed to edit step 4 → Build test-first - each slice goes red to green, so the agent can't quietly break what already worked step 5 → Verify and review - it opens the app in a browser, hunts for leaked keys and security holes, then deletes its own extra code He calls this "agentic engineering" and gave all 20+ skills away for free The human reviews the result, not every step Worth more than most $2,000 agentic engineering courses Save it before your next sprint planning Then read my free course on running 20 agents through a process like this overnight below ↓
Companies pay $300K+ a year for engineers who can run AI agents without babysitting them Last week 20 Claude Code agents shipped 143 changes while I slept. I approved 6 merges Here is graph engineering in Claude Code, file by file. Free ↓
1
4
69
3,558
This is f*cking insane. Elon Musk, the richest man alive, just said the internet already belongs to AI agents: "Agentic traffic already exceeds human traffic online. In 5 years it'll be 1,000x more, and I think even that is underestimating it AI doubles the productivity of every white-collar worker. Then 20 to 30 million robots, each doing the work of 5 people, match the output of the entire US" His endgame: superintelligence pays everyone a universal high income In under 5 minutes, he breaks down why the next economy runs on agents, not office hours Human Traffic → Agent Traffic → Agent Graphs → Robot Workforce → Universal High Income Agent traffic means software that searches, compares and buys for you while nobody clicks a thing Put those agents in a graph and one person runs thousands of them overnight Everyone is still clicking through the internet by hand, almost nobody has agents doing it for them Worth more than a $15K MBA module on the future of work Save and watch it today Then read how I run 20 agents as one graph while I sleep in the article below ↓
Companies pay $300K+ a year for engineers who can run AI agents without babysitting them Last week 20 Claude Code agents shipped 143 changes while I slept. I approved 6 merges Here is graph engineering in Claude Code, file by file. Free ↓
2
27
785
This is f*cking insane. Manus co-founder Tao Zhang, the man whose agent startup Meta tried to buy for $2B: "In 8 months we changed how we hire. AI is already good at doing things, so we don't need more people who are only good at doing things Engineers don't take coding exams here anymore. They get 4 hours and an agent, and the best ones now ship like a team of 8" In 2 minutes, he lays out why Manus deleted every job title inside the company, and why its PMs now ship code while its designers write it Job Titles → Coding Exams → AI Co-Workers → Agent Graphs → One Person, Every Role A coding exam tests what you can do alone A 4-hour session tests what you can ship with a graph of 20 agents behind you Easily worth more than a $1,500 interview bootcamp Save this for the day your company drops job titles Then read my free course on running 20 Claude Code agents overnight below ↓
Companies pay $300K+ a year for engineers who can run AI agents without babysitting them Last week 20 Claude Code agents shipped 143 changes while I slept. I approved 6 merges Here is graph engineering in Claude Code, file by file. Free ↓
4
29
580
This is f*cking insane. Mistral CEO Arthur Mensch, the man running Europe's $21B answer to OpenAI: "Every company now runs on 2 or 3 AI providers. They use the data your systems produce to build better systems, and then they go after your business That's the end game, and it's already priced in" In this 49-minute interview, he explains why renting all your AI from one lab is the fastest way to train your own competitor, and why open models already beat them in many domains Prompts → Agents → Your Data → Their Models → Your Competitor The man building Europe's only frontier lab is telling you exactly who the big labs come for next 95% of companies will hand their best data to the labs, the 5% who own their stack will be the ones still standing Worth more than any $5,000 AI strategy course Bookmark it and send it to someone who still pastes client data into ChatGPT Then read how to run your own graph of agents overnight in the graph engineering guide below ↓
Companies pay $300K+ a year for engineers who can run AI agents without babysitting them Last week 20 Claude Code agents shipped 143 changes while I slept. I approved 6 merges Here is graph engineering in Claude Code, file by file. Free ↓
3
31
666
This is f*cking insane. OpenAI CEO Sam Altman, on stage in Abu Dhabi: "At the start of this year, AI wasn't as smart as our smartest scientists. Now it's smarter than them It couldn't do most white-collar jobs. Now it can do most of them, and we're all still not dreaming big enough" In 10 minutes, he explains why one person now burns 500 billion tokens a month, when six years ago the top user at OpenAI used 100,000 Chat → Agents → Loops → Graphs → 500 Billion Tokens a Month You don't burn that many tokens typing prompts You burn them with a graph of agents that keeps working all night while you sleep This talk is worth more than most $1,000 AI product bootcamps Bookmark it, then watch it with the sound on Then read how to build that overnight agent graph, file by file, in the article below ↓
Companies pay $300K+ a year for engineers who can run AI agents without babysitting them Last week 20 Claude Code agents shipped 143 changes while I slept. I approved 6 merges Here is graph engineering in Claude Code, file by file. Free ↓
6
1
36
1,580
This is f*cking insane. Mira Murati, former CTO of OpenAI: "Every model today is turn-based. You speak, it answers, then it goes away to think, and while it thinks it can't see or hear a thing The next generation never stops listening. Audio, text and video stream in nonstop, and they reply in 20-millisecond chunks" In only 2 minutes, she explains why typing into a chatbot is about to feel as old as a fax machine Typing → Chatbot → Agents → Graphs → AI That Works Beside You Live A turn-based model waits until you stop typing, then goes silent until it's done thinking An interaction model watches and listens to what you do, and can jump in the second you head the wrong way Anyone can write a prompt, almost no one is ready for an AI that is always paying attention Worth more than most $2,000 AI courses Bookmark it and watch it before everyone catches up Then read how graph engineering runs 20 agents overnight in the article below ↓
Companies pay $300K+ a year for engineers who can run AI agents without babysitting them Last week 20 Claude Code agents shipped 143 changes while I slept. I approved 6 merges Here is graph engineering in Claude Code, file by file. Free ↓
1
24
822
Companies pay $300K+ a year for engineers who can run AI agents without babysitting them Last week 20 Claude Code agents shipped 143 changes while I slept. I approved 6 merges Here is graph engineering in Claude Code, file by file. Free ↓
40
32
12
268
266,828
This is f*cking insane. Anthropic hired this engineer at $400K-$1M a year Because he knows how to build harnesses that don't break 99% of people still duct-tape agents together and blame the model when they fall apart In this short workshop, he shows exactly how to build one from scratch Prompts → Agents → Harness → Loops → Graphs step 1 → the harness runs the loop, the context and the sandbox - you stop babysitting the agent step 2 → brain and hands split apart - 60% faster to the first token step 3 → it runs server-side - a crash just resumes from the log step 4 → a failure costs nothing - it retries and replays instead of starting over step 5 → last night's logs turn into new skills - it wakes up smarter every morning Anthropic calls this "dreaming" Most engineers spend weeks hand-rolling this You can copy it tonight Save it and watch it before your next long run Then read how to build agents that never make the same mistake twice in the article below ↓
1
30
957
This is f*cking insane. An Anthropic engineer on the Claude Code team: "If you're sitting there watching Claude write code, you've become the QA tester. That's not what you're paid to do" In 37 minutes, he explains how to take your keyboard out of the hot path completely The key shift is /loop. You tell Claude to wake up every 10 minutes and keep an eye on your PRs, and it does exactly that while you're nowhere near your laptop Routines do the same thing in the cloud, so the work keeps going even with your machine shut He finishes with remote control: any session, on any device, run from your phone Watch it today, then save the full /loop setup guide below
1
1
31
798
CLAUDE SAID "FIXED". THE F*CKING TESTS SAID NO Every AI fix looks done until the bug comes back next week So I stopped trusting "fixed" and built a squad that has to prove it The bug: checkout charged customers twice when the payment retried Opus 5.5 plans, Haiku 5.5 scouts, Sonnet 5.5 builds, Fable 5.1 judges, and a Stop hook decides when the bug is actually dead You drop 3 files into .claude/agents/ and launch: claude --model opus here's how it went: → Opus 5.5 planned it: repro test first, then root cause, then the fix → Haiku 5.5 scouts mapped 188 files and found 2 charge paths with no idempotency key → Sonnet 5.5 wrote the fix and said "fixed" → the Stop hook ran the tests: 31/32, a retry still made 2 charges. Exit 2, not done → Fable 5.1 found the root cause: the key used Date.now(), so every retry got a new key → Sonnet patched it to the order id, tests went 32/32, Fable signed off Without the hook, that "fixed" would have gone to prod The rules that made it work: → no fix without a failing repro test first → same test fails twice? Fable is called in: root cause, or are we just patching the symptom? → Claude can say "fixed", only exit 0 makes it true Opus plans · Haiku scouts · Sonnet builds · Fable judges the full tree > .claude/agents/scout.md → model: haiku · tools: Read, Grep, Glob > .claude/agents/builder.md → model: sonnet · writes the repro test, then the fix > .claude/agents/judge.md → model: claude-fable-5-1 · read-only root-cause reviewer > .claude/settings.json → Stop hook → scripts/verify.sh (exit 2 = not fixed) > Opus 5.5 main session only sees summaries, never raw transcripts paste this prompt into Claude Code ↓ "Set up a bug-fix squad in this repo: 1. Create .claude/agents/scout.md (model: haiku, tools: Read, Grep, Glob) to find every code path involved in a bug 2. Create .claude/agents/builder.md (model: sonnet) that writes a failing repro test FIRST, then the fix, then runs the tests 3. Create .claude/agents/judge.md (model: claude-fable-5-1, read-only tools) for root-cause review: fixing the cause or the symptom? 4. Write scripts/verify.sh (tests + lint, print the reason and exit 2 on failure) and register it as a Stop hook in .claude/settings.json 5. Add to CLAUDE.md: no fix without a red test first, scanning goes to scout, edits go to builder, call judge after the same failure twice and before saying fixed Show every change as a diff first. No edits until I say go" ↳ code.claude.com/docs/en/hook… bookmark it, this is the one you`ll actually use
7
65
2,147