Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

ANTHROPIC'S LEAD ENGINEER LEAKED A $1.2M SYSTEM THAT TURNS ONE ENGINEER INTO A FLEET OF 10 LOOPS your hands were the bottleneck all along - here are 8 steps that change that stop writing, start delegating - loop: feature, loop: bugfix, loop: tests - each runs independently and ships...

Sprytixl's profile picture

Sprytix

5,711 subscribers

61,481 Aufrufe • vor 29 Tagen •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

ANTHROPIC LEAKED 6 RULES THAT RUN 8 LOOPS AT ONCE - AND ONE ENGINEER DOES THE WORK OF A TEAM one engineer with this system replaces an entire team - and costs the company 8 times less You → Opus 5 plan → Fable 5 ×8 execute → Fable 5 review → you: 5 min Opus 5 takes your intent and breaks it into subtasks - a bad plan multiplied across every loop gives the same number of disasters - the plan is the only thing you read carefully one repo - isolated worktrees for each loop - nobody stands on anyone's file - parallel PRs ship while you do nothing the agent runs the tests and fixes until green PR - a red build never reaches your eyes one CLAUDE.md for the whole fleet - without it you get different opinions from every loop and one merge hell the average engineer closes 3-4 tasks a day - this system closes a full sprint overnight with zero working hours Fable 5 pre-reviews every PR before it reaches you - you spend 5 minutes - your throughput is now measured in diffs read per hour bookmark and paste into Claude Code - your first fleet can start tonight
1:15

ANTHROPIC LEAKED 6 RULES THAT RUN 8 LOOPS AT ONCE - AND ONE ENGINEER DOES THE WORK OF A TEAM one engineer with this system replaces an entire team - and costs the company 8 times less You → Opus 5 plan → Fable 5 ×8 execute → Fable 5 review → you: 5 min Opus 5 takes your intent and breaks it into subtasks - a bad plan multiplied across every loop gives the same number of disasters - the plan is the only thing you read carefully one repo - isolated worktrees for each loop - nobody stands on anyone's file - parallel PRs ship while you do nothing the agent runs the tests and fixes until green PR - a red build never reaches your eyes one CLAUDE.md for the whole fleet - without it you get different opinions from every loop and one merge hell the average engineer closes 3-4 tasks a day - this system closes a full sprint overnight with zero working hours Fable 5 pre-reviews every PR before it reaches you - you spend 5 minutes - your throughput is now measured in diffs read per hour bookmark and paste into Claude Code - your first fleet can start tonight

Sprytix

37,904 Aufrufe • vor 27 Tagen

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today
0:50

ANTHROPIC LEAD ENGINEER MAKING $2.3M/YEAR JUST LEAKED A 12-PAGE DOCUMENT - AND GOT FIRED 15 MINUTES AFTER PUBLISHING most developers build loops - but almost every loop breaks in one of five ways, and each failure has a symptom visible from the outside without reading a single line of code > Blind loop - the agent waits for a human to hand it work every morning - automating execution but not discovery > Tangled loop - parallel agents share one directory and overwrite each other parallelism that destroys instead of multiplies > Nodding loop - the agent grades its own work and approves it every time a loop that has never said no to itself is broken > Amnesiac loop - results live only in the context window every morning the system wakes up with no memory of yesterday > Manual loop - no trigger a human presses the button to start it that is not a loop that is a script waiting for a person a real loop finds its own work - remembers what it did has something that can say no never lets two agents touch the same file and fires itself on a timer remove any one of the five - and the loop either breaks or never starts 12 pages that changed how I build agentic systems today

Sprytix

153,690 Aufrufe • vor 1 Monat

ANTHROPIC'S LEAD ENGINEER WON A $1.2M BONUS FOR A SYSTEM THAT TURNS ANY DATA CHAOS INTO A GRAPH IN 8 STEPS raw chaos in - self-updating graph out - and the agent gets +42% productivity from day one Load → Extract → Graph → Index → Query → Memory → Swarm → Update eight steps, one pipeline, graph grows while you sleep documents, code, Slack - everything into one stream through Claude Code - nothing gets lost Fable 5 + Opus 5 extracts entity relationships - Neo4j builds a live structure - zero duplicates three types of search in one answer - vectors, keywords and graph - merged ranking gives accuracy no RAG delivers alone a nightly agent pulls new data and updates the graph automatically - the system gets smarter while you sleep bookmark and paste into Claude Code - a $1.2M system now free
0:53

ANTHROPIC'S LEAD ENGINEER WON A $1.2M BONUS FOR A SYSTEM THAT TURNS ANY DATA CHAOS INTO A GRAPH IN 8 STEPS raw chaos in - self-updating graph out - and the agent gets +42% productivity from day one Load → Extract → Graph → Index → Query → Memory → Swarm → Update eight steps, one pipeline, graph grows while you sleep documents, code, Slack - everything into one stream through Claude Code - nothing gets lost Fable 5 + Opus 5 extracts entity relationships - Neo4j builds a live structure - zero duplicates three types of search in one answer - vectors, keywords and graph - merged ranking gives accuracy no RAG delivers alone a nightly agent pulls new data and updates the graph automatically - the system gets smarter while you sleep bookmark and paste into Claude Code - a $1.2M system now free

Sprytix

483,831 Aufrufe • vor 1 Monat

Anthropic just dropped 1-hour workshop on loop engineering: 1 spec → the loop → 200 features from 0% to 100%: • 10% → 5:31 - Building memory for agentic loops • 30% → 8:22 - Four files for each Loop: features.json, standards.md, progress.md, • 55% → 11:02 - The Loop: check environment → run tests → pick feature → build → test → commit • 80% → 13:06 - one feature per loop. try everything at once and context dies mid-build • 100% → 33:03 - MVP in 1 hour, every next loop under 30 minutes most people build an agent that finishes a task -Anthropic ships agentic loops that can run for days without you. watch it today - then read the full loop engineering playbook below ↓
42:20

Anthropic just dropped 1-hour workshop on loop engineering: 1 spec → the loop → 200 features from 0% to 100%: • 10% → 5:31 - Building memory for agentic loops • 30% → 8:22 - Four files for each Loop: features.json, standards.md, progress.md, • 55% → 11:02 - The Loop: check environment → run tests → pick feature → build → test → commit • 80% → 13:06 - one feature per loop. try everything at once and context dies mid-build • 100% → 33:03 - MVP in 1 hour, every next loop under 30 minutes most people build an agent that finishes a task -Anthropic ships agentic loops that can run for days without you. watch it today - then read the full loop engineering playbook below ↓

Codez

18,398 Aufrufe • vor 21 Tagen

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓
45:37

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

codila

23,915 Aufrufe • vor 1 Monat

While AI timeline argues about loop engineering, a 20-year-old student in Shenzhen built the biggest loop anyone's aimed at money: 300 agents, one brain, $1,200 -> 395,000. Not a prompt. Not a bot. A loop that runs the whole job on its own - and never asks him a thing. No fund. No backers. Just a laptop, a dorm room, and a bet that a swarm beats a genius. His wallet: The smartest single model still works one step at a time. His loop moves in 300 directions at once - and never checks in with him. Claude Opus 4.8 runs the floor as the brain. 300 agents are the hands. One loop ties them together: > Decompose - Opus breaks the market into targets > Dispatch - 300 agents scatter across them at once > Execute - thousands of reads in a single pass, not one by one > Review - Opus grades every edge before a cent moves The hands find. The brain judges. The loop learns what failed and runs again, tighter each time. One daily loss cap, and it shuts itself down. It's not a bot you babysit. It's a loop that runs the whole desk. Everyone's just learning to run one loop. He runs 300 in one. The edge was never the genius model - it's the size of the loop, and the brain in charge of it. Save this - the full 300-agent loop is laid out above, start to finish. You'll want it when you build your own. 300 agents are looping right now, hunting the markets everyone skips. Two clicks and their trades land in your wallet too:
0:53

While AI timeline argues about loop engineering, a 20-year-old student in Shenzhen built the biggest loop anyone's aimed at money: 300 agents, one brain, $1,200 -> 395,000. Not a prompt. Not a bot. A loop that runs the whole job on its own - and never asks him a thing. No fund. No backers. Just a laptop, a dorm room, and a bet that a swarm beats a genius. His wallet: The smartest single model still works one step at a time. His loop moves in 300 directions at once - and never checks in with him. Claude Opus 4.8 runs the floor as the brain. 300 agents are the hands. One loop ties them together: > Decompose - Opus breaks the market into targets > Dispatch - 300 agents scatter across them at once > Execute - thousands of reads in a single pass, not one by one > Review - Opus grades every edge before a cent moves The hands find. The brain judges. The loop learns what failed and runs again, tighter each time. One daily loss cap, and it shuts itself down. It's not a bot you babysit. It's a loop that runs the whole desk. Everyone's just learning to run one loop. He runs 300 in one. The edge was never the genius model - it's the size of the loop, and the brain in charge of it. Save this - the full 300-agent loop is laid out above, start to finish. You'll want it when you build your own. 300 agents are looping right now, hunting the markets everyone skips. Two clicks and their trades land in your wallet too:

cvxv666

53,163 Aufrufe • vor 2 Monaten

FABLE 5 BUILT ME AN AGENT THAT CUT MY WORKDAY FROM 8 HOURS TO 15 MINUTES 6 stages, one loop, runs without me: Triage → Conductor → Worker → Verifier → Gate → Trust Ledger finds the task itself, breaks it into steps in seconds, writes the code, checks the result, passes or rejects, records and learns 3 out of 4 tasks passed first try - the system knows where it failed and fixes it 8 hours of work → 15 minutes of watching Fable 5, pure HTML and JS, zero external libraries - and an agent that never stops
0:44

FABLE 5 BUILT ME AN AGENT THAT CUT MY WORKDAY FROM 8 HOURS TO 15 MINUTES 6 stages, one loop, runs without me: Triage → Conductor → Worker → Verifier → Gate → Trust Ledger finds the task itself, breaks it into steps in seconds, writes the code, checks the result, passes or rejects, records and learns 3 out of 4 tasks passed first try - the system knows where it failed and fixes it 8 hours of work → 15 minutes of watching Fable 5, pure HTML and JS, zero external libraries - and an agent that never stops

Noisy

98,722 Aufrufe • vor 1 Monat

PROMPTS ARE DEAD. LOOPS JUST REPLACED YOUR $200K ENGINEER. Claire Vo showed how to turn one prompt into a self-running loop. It reviews your aging pull requests every morning and hunts for new skills every week. And it spins up its own subagents to check its own work. Runs on Claude Code + Codex. One afternoon. One prompt. The numbers are insane: - Senior doing code review: $200K/year - Automation engineer: $150K/year - This setup: about $200/month - Time to build: one afternoon - Skill required: describe the job like you are onboarding a hire The opportunity is even wilder: Teams pay people to babysit pull requests and chase stale reviews. The loop does it itself at 10:15 a.m., alerts the team, and validates itself with subagents. An agency would charge thousands to wire this up. One person + Claude Code + Codex + one prompt = an engineering team that reviews code and finds new skills while you sleep. Save and watch the clip.
29:06

PROMPTS ARE DEAD. LOOPS JUST REPLACED YOUR $200K ENGINEER. Claire Vo showed how to turn one prompt into a self-running loop. It reviews your aging pull requests every morning and hunts for new skills every week. And it spins up its own subagents to check its own work. Runs on Claude Code + Codex. One afternoon. One prompt. The numbers are insane: - Senior doing code review: $200K/year - Automation engineer: $150K/year - This setup: about $200/month - Time to build: one afternoon - Skill required: describe the job like you are onboarding a hire The opportunity is even wilder: Teams pay people to babysit pull requests and chase stale reviews. The loop does it itself at 10:15 a.m., alerts the team, and validates itself with subagents. An agency would charge thousands to wire this up. One person + Claude Code + Codex + one prompt = an engineering team that reviews code and finds new skills while you sleep. Save and watch the clip.

shmidt

51,155 Aufrufe • vor 1 Monat

ANTHROPIC LEAKED A SETUP WHERE ONE FILE STARTS 7 LOOPS THAT TURN A PROMPT INTO A WORKING BUSINESS AI engineer drops in 1 file - the other 95% of the work closes automatically without them. spec → tasks → code → tests → docs → release → monitoring → back into the spec you don't write tickets anymore - you write the thing tickets get derived from, and Opus 5 cuts the spec into 6 tasks by itself. a task that fails its test comes back to itself, not to you - and runs a second lap without a single notification. 6 lanes of code run in parallel and none of them wait on you - the critic filters the diff before you ever open it. every new production bug becomes a permanent line in the eval set - the system never steps on it twice. monitoring isn't the end of the line, it's the start of the next spec - those back edges are what make it a graph instead of a conveyor. and one place is left where you say yes - release, 5 minutes instead of 5 hours. save this and paste it into Claude Code - and you get 7 loops that run without you ↓
0:52

ANTHROPIC LEAKED A SETUP WHERE ONE FILE STARTS 7 LOOPS THAT TURN A PROMPT INTO A WORKING BUSINESS AI engineer drops in 1 file - the other 95% of the work closes automatically without them. spec → tasks → code → tests → docs → release → monitoring → back into the spec you don't write tickets anymore - you write the thing tickets get derived from, and Opus 5 cuts the spec into 6 tasks by itself. a task that fails its test comes back to itself, not to you - and runs a second lap without a single notification. 6 lanes of code run in parallel and none of them wait on you - the critic filters the diff before you ever open it. every new production bug becomes a permanent line in the eval set - the system never steps on it twice. monitoring isn't the end of the line, it's the start of the next spec - those back edges are what make it a graph instead of a conveyor. and one place is left where you say yes - release, 5 minutes instead of 5 hours. save this and paste it into Claude Code - and you get 7 loops that run without you ↓

Sprytix

66,250 Aufrufe • vor 14 Tagen

ANTHROPIC SPENT $2.3M ON A LOOP MANUAL WITH 7 PRINCIPLES THAT TURN AN AGENT INTO A MULTI-TASK ASSISTANT 4 years of development and 1000+ hours of lectures - now anyone can launch an agent that earns instead of falls Simplicity → Tool Design → Evaluation → Disclosure → Orchestration → Stop Conditions start with the simplest solution - one call x1, workflow x4, agent x15 - most tasks never needed an agent at all 60% of failures come from a tool written vaguely - clear parameters complete the task that vague ones stop the agent generates, grades itself and returns with notes if wrong - without this the first answer is always the final one 50 tools in context and the agent gets confused - give it 3 relevant ones and it completes the task Opus 5 plans, Fable 5 executes in parallel - parallelism wins only when subtasks do not depend on each other without a turn limit the agent can burn $10,000 overnight and you find out in the morning when nothing can be changed bookmark & paste into Claude Code today - tomorrow the agent earns instead of falls
0:48

ANTHROPIC SPENT $2.3M ON A LOOP MANUAL WITH 7 PRINCIPLES THAT TURN AN AGENT INTO A MULTI-TASK ASSISTANT 4 years of development and 1000+ hours of lectures - now anyone can launch an agent that earns instead of falls Simplicity → Tool Design → Evaluation → Disclosure → Orchestration → Stop Conditions start with the simplest solution - one call x1, workflow x4, agent x15 - most tasks never needed an agent at all 60% of failures come from a tool written vaguely - clear parameters complete the task that vague ones stop the agent generates, grades itself and returns with notes if wrong - without this the first answer is always the final one 50 tools in context and the agent gets confused - give it 3 relevant ones and it completes the task Opus 5 plans, Fable 5 executes in parallel - parallelism wins only when subtasks do not depend on each other without a turn limit the agent can burn $10,000 overnight and you find out in the morning when nothing can be changed bookmark & paste into Claude Code today - tomorrow the agent earns instead of falls

Sprytix

27,543 Aufrufe • vor 28 Tagen

ANTHROPIC LEAKED 8 RULES THAT GIVE ONE ENGINEER 8X FROM A SINGLE CHANGE the engineers built it so nothing adds up - it multiplies, and that's the 8x task → split → verify → score → write back one queue means you wait for every step in turn - three workers together cost you the slowest one, not the sum of all. as long as you're the one reading the diff, the bottleneck is you, not the model. state is written at every step - a crash mid-run costs you one step, not the whole session. history gets compressed 25 times over - the next pass starts at 8k instead of 200k. nothing moves forward without a number - "it got better" isn't a result, and the breakage comes back when you're no longer watching. the eighth rule is the only one that writes back into CLAUDE.md - the agent records what it learned, and the next run doesn't start from zero. copy this into Claude Code today - and tomorrow you work like an engineer on $1.5M a year ↓
1:05

ANTHROPIC LEAKED 8 RULES THAT GIVE ONE ENGINEER 8X FROM A SINGLE CHANGE the engineers built it so nothing adds up - it multiplies, and that's the 8x task → split → verify → score → write back one queue means you wait for every step in turn - three workers together cost you the slowest one, not the sum of all. as long as you're the one reading the diff, the bottleneck is you, not the model. state is written at every step - a crash mid-run costs you one step, not the whole session. history gets compressed 25 times over - the next pass starts at 8k instead of 200k. nothing moves forward without a number - "it got better" isn't a result, and the breakage comes back when you're no longer watching. the eighth rule is the only one that writes back into CLAUDE.md - the agent records what it learned, and the next run doesn't start from zero. copy this into Claude Code today - and tomorrow you work like an engineer on $1.5M a year ↓

Noisy

37,058 Aufrufe • vor 16 Tagen

The creator of Claude Code deleted his IDE in November 2024. In the last 30 days, 100% of his contributions were written by Claude Code. 259 PRs. His job is not prompting anymore. His job is writing loops that prompt Claude for him. Here is what that progression actually looks like: → stage 1: write code by hand with autocomplete → stage 2: run 5-10 claude sessions in parallel, prompt each one yourself → stage 3: write loops that prompt claude — you become the author, the model becomes a subroutine → the ralph loop (2025): bash one-liner, fixed anchor files, built a programming language for $297 → the 2026 loop: loops supervising loops, scheduling on infrastructure time, git-backed durable state → five building blocks: automations, durable state, validator split, loop orchestration, crash recovery Most developers are still in stage 2, prompting sessions by hand. The ones at stage 3 are writing the loops that do the prompting for them. Read this article to be ahead of the curve! Follow NeilXbt for more AI engineering intelligence that shows you exactly where the leverage moved and what building at that level actually looks like.
1:00

The creator of Claude Code deleted his IDE in November 2024. In the last 30 days, 100% of his contributions were written by Claude Code. 259 PRs. His job is not prompting anymore. His job is writing loops that prompt Claude for him. Here is what that progression actually looks like: → stage 1: write code by hand with autocomplete → stage 2: run 5-10 claude sessions in parallel, prompt each one yourself → stage 3: write loops that prompt claude — you become the author, the model becomes a subroutine → the ralph loop (2025): bash one-liner, fixed anchor files, built a programming language for $297 → the 2026 loop: loops supervising loops, scheduling on infrastructure time, git-backed durable state → five building blocks: automations, durable state, validator split, loop orchestration, crash recovery Most developers are still in stage 2, prompting sessions by hand. The ones at stage 3 are writing the loops that do the prompting for them. Read this article to be ahead of the curve! Follow NeilXbt for more AI engineering intelligence that shows you exactly where the leverage moved and what building at that level actually looks like.

NeilXbt

11,556 Aufrufe • vor 2 Monaten

Andrew Ng just released a 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents that loop, rewrite themselves, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it done. Andrew Ng is already teaching everything after: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow. Systems that improve and run without you are the new one. This 2-hour watch is worth more than most $500 agent engineering courses. Bookmark and watch it before everyone catches up. Then read how to run 1,000 agents from one prompt below ↓
1:48:23

Andrew Ng just released a 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents that loop, rewrite themselves, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it done. Andrew Ng is already teaching everything after: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow. Systems that improve and run without you are the new one. This 2-hour watch is worth more than most $500 agent engineering courses. Bookmark and watch it before everyone catches up. Then read how to run 1,000 agents from one prompt below ↓

Lunar

223,862 Aufrufe • vor 15 Tagen

garry tan just open-sourced a 128k-star repo that basically turns claude code into your entire engineering org it’s called gstack: 23 tools that break a single claude workflow into product, engineering, qa, review, and release lanes > /office-hours turns a rough idea into a real product spec > /plan-ceo-review + /plan-eng-review try to tear the plan apart before any code ships > /review hunts for bugs and patches them > /qa spins up an actual browser and tests the app end to end > /ship runs the final checks and pushes the pr think → plan → build → review → test → ship → reflect garry says this setup let him ship 3 production services and 40+ features in 60 days while still running yc full-time one developer sets the compass. the repo runs the loop.
0:36

garry tan just open-sourced a 128k-star repo that basically turns claude code into your entire engineering org it’s called gstack: 23 tools that break a single claude workflow into product, engineering, qa, review, and release lanes > /office-hours turns a rough idea into a real product spec > /plan-ceo-review + /plan-eng-review try to tear the plan apart before any code ships > /review hunts for bugs and patches them > /qa spins up an actual browser and tests the app end to end > /ship runs the final checks and pushes the pr think → plan → build → review → test → ship → reflect garry says this setup let him ship 3 production services and 40+ features in 60 days while still running yc full-time one developer sets the compass. the repo runs the loop.

CyrilXBT

20,844 Aufrufe • vor 13 Tagen

Karpathy just proved the structure beats the model - mapped the whole path from loops to graphs into a 15-page PDF: he pointed one agent at code he'd already hand-optimized. 700 experiments in two days, then he said the single loop was never the target here's the full system: step 1 → write the scorer before anything else. one number, automatic, under 10 minutes. no scorer, no loop step 2 → split the files. one the agent edits, one holding the scorer it can never reach step 3 → fix the wall clock per attempt. comparability comes from the budget, not the attempts step 4 → write the never-stop line verbatim or your agent becomes a slower human step 5 → add a second agent only after the first ships real commits. one git worktree each or they overwrite each other step 6 → at thirty agents, isolation costs more than it saves. that's when they need one shared DAG instead of thirty private histories 2.02 hours to 1.80 hours on code its author had already tuned. 90,900 stars in four months. read this PDF and paste it into your Claude, you won't regret it bookmark, then read the article on building graphs from scratch ↓
2:00

Karpathy just proved the structure beats the model - mapped the whole path from loops to graphs into a 15-page PDF: he pointed one agent at code he'd already hand-optimized. 700 experiments in two days, then he said the single loop was never the target here's the full system: step 1 → write the scorer before anything else. one number, automatic, under 10 minutes. no scorer, no loop step 2 → split the files. one the agent edits, one holding the scorer it can never reach step 3 → fix the wall clock per attempt. comparability comes from the budget, not the attempts step 4 → write the never-stop line verbatim or your agent becomes a slower human step 5 → add a second agent only after the first ships real commits. one git worktree each or they overwrite each other step 6 → at thirty agents, isolation costs more than it saves. that's when they need one shared DAG instead of thirty private histories 2.02 hours to 1.80 hours on code its author had already tuned. 90,900 stars in four months. read this PDF and paste it into your Claude, you won't regret it bookmark, then read the article on building graphs from scratch ↓

Carnage

53,872 Aufrufe • vor 28 Tagen

ANTHROPIC LEAKED A 6-AGENT SETUP THAT TURNS ONE PROMPT INTO A FINISHED PR your name shows up in this process exactly once - at the very end, for 5 minutes. spec → planner → 3 builders → critic → scribe → PR → back into the spec the planner runs once and the whole line inherits its decisions - a bad plan executed by five perfect agents is still a bad result. 3 lanes build in parallel - and they only work because the planner cut the steps so none of them reads another's output. tests loop until green and red goes back to the coder - the critic never sees a broken build. the critic rejects to the plan, not the code - tests ask does it run, the critic asks should it exist. the scribe writes the PR from the trace, not from memory - cut this seat and you get 8 PRs nobody can tell apart. the back edge into the spec is the whole trick - today's failures become tomorrow's constraints without you typing them. one human step in the whole thing: approve or send back - 5 minutes instead of 5 hours. save this and read the full graph engineering course below ↓
0:52

ANTHROPIC LEAKED A 6-AGENT SETUP THAT TURNS ONE PROMPT INTO A FINISHED PR your name shows up in this process exactly once - at the very end, for 5 minutes. spec → planner → 3 builders → critic → scribe → PR → back into the spec the planner runs once and the whole line inherits its decisions - a bad plan executed by five perfect agents is still a bad result. 3 lanes build in parallel - and they only work because the planner cut the steps so none of them reads another's output. tests loop until green and red goes back to the coder - the critic never sees a broken build. the critic rejects to the plan, not the code - tests ask does it run, the critic asks should it exist. the scribe writes the PR from the trace, not from memory - cut this seat and you get 8 PRs nobody can tell apart. the back edge into the spec is the whole trick - today's failures become tomorrow's constraints without you typing them. one human step in the whole thing: approve or send back - 5 minutes instead of 5 hours. save this and read the full graph engineering course below ↓

Hanako

162,771 Aufrufe • vor 12 Tagen

Andrew Ng: "if I had to pick one technology today - it's graphs of self-improving agents I have 4 patterns that necessary" here are 4 rules: rule 1 → reflection make the agent critique its own output, find problems, rewrite - one loop of self-review beats a smarter model with no review rule 2 → tool use - don't just think, act - give the agent search, code execution, APIs - thinking without tools is guessing rule 3 → planning - break complex tasks into steps before executing - agents that plan first solve what agents that rush can't rule 4 → multi-agent collaboration - don't run one agent run a team: one writes code, another critiques it, another tests many people overlook these crucial rules behind every smart agent save this - then read how to wire these 4 rules into one graph ↓
31:20

Andrew Ng: "if I had to pick one technology today - it's graphs of self-improving agents I have 4 patterns that necessary" here are 4 rules: rule 1 → reflection make the agent critique its own output, find problems, rewrite - one loop of self-review beats a smarter model with no review rule 2 → tool use - don't just think, act - give the agent search, code execution, APIs - thinking without tools is guessing rule 3 → planning - break complex tasks into steps before executing - agents that plan first solve what agents that rush can't rule 4 → multi-agent collaboration - don't run one agent run a team: one writes code, another critiques it, another tests many people overlook these crucial rules behind every smart agent save this - then read how to wire these 4 rules into one graph ↓

codila

97,472 Aufrufe • vor 1 Monat

THE HEAD ENGINEER AT ANTHROPIC LEAKED A SETUP WHERE ONE FILE TURNS INTO A FINISHED PRODUCT IN 24 HOURS you hire nobody - you paste a $3.2M file into Fable 5, and the system unrolls itself from there. root → wiring → 4 branches → tests → release → back into the root in the first hour you write 4 things: boundaries, stack, roles, escalation - everything downstream is a consequence of that file. the first 5 hours the system wires itself into tools and only then decides what to build - a team would spread that across two weeks. 8 straight hours run 4 parallel branches with zero meetings - the same block a team fills with standups. by the time you finally open the diff, tests and the critic have already rejected it twice. the changelog is written by the run, not by a human from memory - so it never falls behind the code. your total involvement across the day is exactly 2 hours: the first one, and the one where you say ship it. the 9 hours you were asleep weren't downtime, they were capacity - a queue you have to launch by hand becomes your monday. and the key part: at 05:00 the report rewrites that same root - what shipped, what got rejected, what it cost. without that last line this is just a schedule - with it, the schedule improves itself. save this and paste it into Claude Code - and tomorrow starts from a better file than today did ↓
0:50

THE HEAD ENGINEER AT ANTHROPIC LEAKED A SETUP WHERE ONE FILE TURNS INTO A FINISHED PRODUCT IN 24 HOURS you hire nobody - you paste a $3.2M file into Fable 5, and the system unrolls itself from there. root → wiring → 4 branches → tests → release → back into the root in the first hour you write 4 things: boundaries, stack, roles, escalation - everything downstream is a consequence of that file. the first 5 hours the system wires itself into tools and only then decides what to build - a team would spread that across two weeks. 8 straight hours run 4 parallel branches with zero meetings - the same block a team fills with standups. by the time you finally open the diff, tests and the critic have already rejected it twice. the changelog is written by the run, not by a human from memory - so it never falls behind the code. your total involvement across the day is exactly 2 hours: the first one, and the one where you say ship it. the 9 hours you were asleep weren't downtime, they were capacity - a queue you have to launch by hand becomes your monday. and the key part: at 05:00 the report rewrites that same root - what shipped, what got rejected, what it cost. without that last line this is just a schedule - with it, the schedule improves itself. save this and paste it into Claude Code - and tomorrow starts from a better file than today did ↓

Sprytix

20,510 Aufrufe • vor 11 Tagen

ANTHROPIC LEAKED A FILE WHERE 8 ENGINEERS COST $2.40 A DAY INSTEAD OF $120,000 A MONTH Microsoft and Google already run this - the same 8 seats cost them $73 a month. the ring turns once a day, 3 shifts hand off the work, zero meetings. the scout has tomorrow's agenda ready before you sit down. the architect splits the work, 2 builders run parallel branches. contracts get written before the workers - skip that and every worker guesses what the last one meant. with contracts all three read one shape: what goes in, what comes out. 3 branches at once means you pay the slowest lane, not the sum of three. nothing reaches you unrejected: the cheap model asks does it run, the expensive one asks should it merge. a gate that never rejects anything is a status badge, not a gate. the night crew takes the long jobs that never fit a working day. 1 role out of 8 writes back into the file - cut that edge and the rest repeat monday for a year. save this and paste it into Claude Code - you write the file, the file runs the company ↓
1:30

ANTHROPIC LEAKED A FILE WHERE 8 ENGINEERS COST $2.40 A DAY INSTEAD OF $120,000 A MONTH Microsoft and Google already run this - the same 8 seats cost them $73 a month. the ring turns once a day, 3 shifts hand off the work, zero meetings. the scout has tomorrow's agenda ready before you sit down. the architect splits the work, 2 builders run parallel branches. contracts get written before the workers - skip that and every worker guesses what the last one meant. with contracts all three read one shape: what goes in, what comes out. 3 branches at once means you pay the slowest lane, not the sum of three. nothing reaches you unrejected: the cheap model asks does it run, the expensive one asks should it merge. a gate that never rejects anything is a status badge, not a gate. the night crew takes the long jobs that never fit a working day. 1 role out of 8 writes back into the file - cut that edge and the rest repeat monday for a year. save this and paste it into Claude Code - you write the file, the file runs the company ↓

Sprytix

696,941 Aufrufe • vor 5 Tagen

ANTHROPIC LEAKED A SETUP THAT COST OVER $3.2M - AN AI BUSINESS BUILT IN 24 HOURS WITH 10 WORKERS, $100K IN THE FIRST MONTH your share of the cycle is 3 hours out of 24 - the rest is closed by 10 roles without you. root → 3 builders → tester and critic → queue → scout → back into the root at the start you write 3 things no model will write for you: who buys, what we sell, at what price. get those wrong and the next 20 hours automate the wrong business perfectly. 3 builders run in parallel: the product, the landing page, the integrations - the block a real team fills with standups. by the time you look, the build has been rejected twice: Sonnet 5 asks does it run, Opus 5 asks should it ship at all. a gate that never rejects anything is a status badge, not a gate. your entire involvement in the assembly phase is one yes on the release - about a minute. the copywriter queues a week of content on day one - the queue is what keeps day 9 from being the day you stopped posting. the scout on Haiku 4.5 is the only role that never stops - it listens where your buyer already complains. the analyst returns 3 numbers and rewrites the root file - without that edge this is a work schedule, not a loop. save this and paste it into Claude Code - a day builds the machine, the offer decides the number ↓
1:14

ANTHROPIC LEAKED A SETUP THAT COST OVER $3.2M - AN AI BUSINESS BUILT IN 24 HOURS WITH 10 WORKERS, $100K IN THE FIRST MONTH your share of the cycle is 3 hours out of 24 - the rest is closed by 10 roles without you. root → 3 builders → tester and critic → queue → scout → back into the root at the start you write 3 things no model will write for you: who buys, what we sell, at what price. get those wrong and the next 20 hours automate the wrong business perfectly. 3 builders run in parallel: the product, the landing page, the integrations - the block a real team fills with standups. by the time you look, the build has been rejected twice: Sonnet 5 asks does it run, Opus 5 asks should it ship at all. a gate that never rejects anything is a status badge, not a gate. your entire involvement in the assembly phase is one yes on the release - about a minute. the copywriter queues a week of content on day one - the queue is what keeps day 9 from being the day you stopped posting. the scout on Haiku 4.5 is the only role that never stops - it listens where your buyer already complains. the analyst returns 3 numbers and rewrites the root file - without that edge this is a work schedule, not a loop. save this and paste it into Claude Code - a day builds the machine, the offer decides the number ↓

Sprytix

22,666 Aufrufe • vor 6 Tagen