Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

ANTHROPIC LEAKED A 5-AGENT SETUP THAT TURNS ONE QUESTION INTO A SOURCED REPORT you write one line and never open a tab - the fleet reads 40 sources and only the answer comes back. question → scope → 5 searchers → dedupe → writer → fact-check → report the... scope agent turns a vague question into 5 angles that do not overlap - skip this and five agents fetch the same three articles. 5 searchers run in parallel with separate contexts - none of them sees what the others found, which is exactly why they do not converge on the same source. dedupe is code, not an agent - flatten, drop repeats, normalize URLs, zero tokens, instant. the writer only sees structured findings, never raw pages - it cannot cite something that was never verified because it never had access to it. the fact-checker reads the draft against the sources, not against itself - every claim without a matching source goes back, and only that section is rewritten. nothing reaches you until a second agent, with clean context, has tried to kill it. 12 minutes, 40 sources, one report where every line traces back to something real. save this and read the full graph engineering course below ↓show more

Hanako

19,043 subscribers

59,030 просмотров • 1 месяц назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 11

Фото профиля Hussain Hashim | Building SundayBack

Hussain Hashim | Building SundayBack1 месяц назад

@hanakoxbt that's wild! feel like i need this setup for all the random questions i end up googling daily. game changer for info junkies like me.

Фото профиля cvxv666

cvxv6661 месяц назад

saved it, real hidden alpha

Фото профиля AI Mastery Guide

AI Mastery Guide1 месяц назад

40 sources in 12 minutes

Фото профиля ∑: Meww ∑: (❖,❖)

∑: Meww ∑: (❖,❖)1 месяц назад

Fascinating breakdown of Anthropic's advanced AI reporting process.

Фото профиля Wystra

Wystra1 месяц назад

5 agents 40 sources and the writer still gets the cleanest signal

Фото профиля Gipp 🦅

Gipp 🦅1 месяц назад

clean contexts prevent five searchers sharing blind spots

Фото профиля kadd

kadd1 месяц назад

Saved. Thanks man

Фото профиля Abhimanyu Vaishnav

Abhimanyu Vaishnav1 месяц назад

This is pure engineering gold. The real unlock isn’t just “5 agents” - it’s the hard isolation + treating dedupe as pure code. Most multi-agent setups collapse because agents start sharing context and converge on the same 3 sources. Here the searchers never see each other, the writer never sees raw pages, and the fact-checker gets a clean slate specifically to try and kill the draft. That’s how you actually ship sourced reports instead of polished hallucinations. Saving this architecture.

Фото профиля symphony

symphony1 месяц назад

Saved, thanks 🙏

Фото профиля Cryton

Cryton1 месяц назад

The strongest part is the separation of research and verification. Independent context makes confirmation bias harder to propagate.

Фото профиля slash1s

slash1s1 месяц назад

need to save this leak..

Похожие видео

ANTHROPIC LEAKED A 4-AGENT SETUP THAT CUTS A CODEBASE AUDIT FROM 3 DAYS TO 20 MINUTES you point it at a repo and walk away - it comes back with what breaks, ranked, patches already tested. repo → map → 4 auditors → rank → fix → verify → report → back into the map the map cuts the repo by blast radius, not by folder - skip it and four agents audit the same three files and miss the one that ships broken. 4 auditors run in parallel with separate contexts - deps, secrets, dead code, hot paths, and none of them sees another's findings. rank is code, not an agent - sort by what breaks production, drop the duplicates, zero tokens. the fixer only opens patches for the top slice - a hundred findings nobody acts on is a report, not an audit. verify runs the suite on every patch and red goes back to the fixer - that patch only, never the whole batch. the back edge into the map is the whole trick - accepted findings become rules, so next week starts where this one ended. one human step in all of it: which fixes ship - 20 minutes instead of 3 days. save this and read the full graph engineering course below ↓

ANTHROPIC LEAKED A 4-AGENT SETUP THAT CUTS A CODEBASE AUDIT FROM 3 DAYS TO 20 MINUTES you point it at a repo and walk away - it comes back with what breaks, ranked, patches already tested. repo → map → 4 auditors → rank → fix → verify → report → back into the map the map cuts the repo by blast radius, not by folder - skip it and four agents audit the same three files and miss the one that ships broken. 4 auditors run in parallel with separate contexts - deps, secrets, dead code, hot paths, and none of them sees another's findings. rank is code, not an agent - sort by what breaks production, drop the duplicates, zero tokens. the fixer only opens patches for the top slice - a hundred findings nobody acts on is a report, not an audit. verify runs the suite on every patch and red goes back to the fixer - that patch only, never the whole batch. the back edge into the map is the whole trick - accepted findings become rules, so next week starts where this one ended. one human step in all of it: which fixes ship - 20 minutes instead of 3 days. save this and read the full graph engineering course below ↓

Hanako

137,040 просмотров • 1 месяц назад

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 ↓

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

164,222 просмотров • 1 месяц назад

ANTHROPIC LEAKED A BOT THAT READS 100 SOURCES FOR YOU AND HANDS BACK ONE PARAGRAPH IN 90 SECONDS it reads a hundred sources, you read one paragraph - and in week one that turned $10 into $10,000 root → feed → filter → contradictions → digest → back to root 5 blocks of 12 minutes, 100 sources in, 1 paragraph out you write the root yourself: what gets tracked, which sources, and what never gets in Grok 4.6 pulls the news at the moment of publication, because market news has a shelf life of minutes before the aggregators Haiku 4.5 cuts the noise and throws out the same story that arrived seven times over Opus 5 builds the block nobody else builds - not what happened, but who disagrees with whom a contradiction is a question with a source attached, and it's the only output worth a human minute what did not hold up yesterday rewrites what gets tracked today exactly four things come out: the digest, the calendar, the contradictions and yesterday's failures what never comes out: a signal, an order, a position size, and not one word telling you to buy 0 decisions are made for you, and that is exactly why this file can be trusted save this and paste it into Claude Code - let it build your root ↓

ANTHROPIC LEAKED A BOT THAT READS 100 SOURCES FOR YOU AND HANDS BACK ONE PARAGRAPH IN 90 SECONDS it reads a hundred sources, you read one paragraph - and in week one that turned $10 into $10,000 root → feed → filter → contradictions → digest → back to root 5 blocks of 12 minutes, 100 sources in, 1 paragraph out you write the root yourself: what gets tracked, which sources, and what never gets in Grok 4.6 pulls the news at the moment of publication, because market news has a shelf life of minutes before the aggregators Haiku 4.5 cuts the noise and throws out the same story that arrived seven times over Opus 5 builds the block nobody else builds - not what happened, but who disagrees with whom a contradiction is a question with a source attached, and it's the only output worth a human minute what did not hold up yesterday rewrites what gets tracked today exactly four things come out: the digest, the calendar, the contradictions and yesterday's failures what never comes out: a signal, an order, a position size, and not one word telling you to buy 0 decisions are made for you, and that is exactly why this file can be trusted save this and paste it into Claude Code - let it build your root ↓

Noisy

12,297 просмотров • 1 месяц назад

Found a setup that replaces a team of researchers with 300 AI agents and one shared graph. the interesting part is what happens after all 300 come back with different pieces of the answer. because now you don’t have 300 agents. you have: 300 outputs → hundreds of sources → repeated entities → overlapping claims → contradictions → thousands of possible relationships and all of that has to collapse into one structure. that’s what the context graph is doing. instead of: agent → report you get: agents → sources → entities → edges → contradictions → verification → one graph every source becomes a node. every shared entity creates a connection. 300 agents can create information. the graph is what turns that information into memory the next agent can actually use. that’s the anatomy behind the setup ↓

Found a setup that replaces a team of researchers with 300 AI agents and one shared graph. the interesting part is what happens after all 300 come back with different pieces of the answer. because now you don’t have 300 agents. you have: 300 outputs → hundreds of sources → repeated entities → overlapping claims → contradictions → thousands of possible relationships and all of that has to collapse into one structure. that’s what the context graph is doing. instead of: agent → report you get: agents → sources → entities → edges → contradictions → verification → one graph every source becomes a node. every shared entity creates a connection. 300 agents can create information. the graph is what turns that information into memory the next agent can actually use. that’s the anatomy behind the setup ↓

Ricker

19,999 просмотров • 1 месяц назад

THE ANATOMY OF A SECOND BRAIN THAT WRITES ITSELF one Obsidian vault, three layers, and a loop that files every good answer back into a wiki you never touch the structure: > CLAUDE.md + AGENTS.md - the constitution. same rules whether Claude or Codex runs the loop > raw/ - inbox, articles, assets. frozen and read-only, you feed it and walk away > wiki/ - index.md, entities/, concepts/, synthesis.md. the agent grows this on its own > log.md - append-only, every move timestamped 47 sources in -> 210 pages out the agent typed 96% of it. you typed zero the cost trick: point Opus 5 only at synthesis.md, the one file that needs frontier reasoning. everything else runs fine on cheaper models under the hood it's loop engineering: you ask -> a good answer gets filed back -> the wiki grows start linking entities to each other and you're one step from a full graph your research compounds while you sleep. the full blueprint is below 👇

THE ANATOMY OF A SECOND BRAIN THAT WRITES ITSELF one Obsidian vault, three layers, and a loop that files every good answer back into a wiki you never touch the structure: > CLAUDE.md + AGENTS.md - the constitution. same rules whether Claude or Codex runs the loop > raw/ - inbox, articles, assets. frozen and read-only, you feed it and walk away > wiki/ - index.md, entities/, concepts/, synthesis.md. the agent grows this on its own > log.md - append-only, every move timestamped 47 sources in -> 210 pages out the agent typed 96% of it. you typed zero the cost trick: point Opus 5 only at synthesis.md, the one file that needs frontier reasoning. everything else runs fine on cheaper models under the hood it's loop engineering: you ask -> a good answer gets filed back -> the wiki grows start linking entities to each other and you're one step from a full graph your research compounds while you sleep. the full blueprint is below 👇

Annatar.md

23,649 просмотров • 22 дней назад

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 ↓

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

66,333 просмотров • 1 месяц назад

one agent → a loop → a graph → a system that throttles itself Google just put the whole ladder in one free course. most people never leave the first rung. 2 hours 4 minutes, taught by two Google Cloud engineers. no signup, no paywall. 17:55 - build your first agent 39:55 - loop engineering: iterate, check, break 1:13:25 - graph engineering 1:35:27 - agents that throttle themselves 1:56:19 - the full graph for multi-agent systems the fourth one is the step nobody talks about. an agent that cannot throttle itself is not autonomous, it is just unattended. everyone builds one agent and calls it done. this is the version where the agents wire themselves into a graph and decide their own rate. and the thing that decides when one of them is allowed to stop is not in the course. that part you build yourself. bookmark and watch it today, then read the eval setup below

one agent → a loop → a graph → a system that throttles itself Google just put the whole ladder in one free course. most people never leave the first rung. 2 hours 4 minutes, taught by two Google Cloud engineers. no signup, no paywall. 17:55 - build your first agent 39:55 - loop engineering: iterate, check, break 1:13:25 - graph engineering 1:35:27 - agents that throttle themselves 1:56:19 - the full graph for multi-agent systems the fourth one is the step nobody talks about. an agent that cannot throttle itself is not autonomous, it is just unattended. everyone builds one agent and calls it done. this is the version where the agents wire themselves into a graph and decide their own rate. and the thing that decides when one of them is allowed to stop is not in the course. that part you build yourself. bookmark and watch it today, then read the eval setup below

Hanako

53,692 просмотров • 2 месяцев назад

Loops vs. Graphs, clearly explained! loops are great, but they have a ceiling: a loop makes one unit of work better. it cannot decide which units exist. so you end up with a very good agent running the wrong three steps, in the wrong order, one at a time. Graph engineering fixes this by moving the decision up a layer: what runs, what runs at the same time, and what never runs at all. you need both. here's how it works: a graph splits your system into two kinds of decision. ↳ inside a unit: the loop. produce, check, correct, repeat until green ↳ between units: the graph. split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs you get parallel work, isolated contexts, and steps that stop running when nothing needs them. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. a graph where every edge is an agent pays rent on its own wiring. one thing to know before you scale it. a graph has two return paths, and almost everyone builds one. ↳ the correction edge is short. a gate rejects one unit back to the step that produced it, and it fixes the run you are in ↳ the learning edge is long. an accepted result goes back to the splitter as a constraint, and it fixes every run after skip the second and you get a graph that is fast and never gets smarter. next week it starts from the same place with the same blind spots. and a smaller one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Loops vs. Graphs, clearly explained! loops are great, but they have a ceiling: a loop makes one unit of work better. it cannot decide which units exist. so you end up with a very good agent running the wrong three steps, in the wrong order, one at a time. Graph engineering fixes this by moving the decision up a layer: what runs, what runs at the same time, and what never runs at all. you need both. here's how it works: a graph splits your system into two kinds of decision. ↳ inside a unit: the loop. produce, check, correct, repeat until green ↳ between units: the graph. split, fan out, merge, gate, send back Prompts → Context → Harness → Loops → Graphs you get parallel work, isolated contexts, and steps that stop running when nothing needs them. the trick is being selective about what becomes a node. only spend a model where judgment lives. merging, ranking, deduping and schema checks are edges, and edges are code. free, instant, and they cannot be argued out of a verdict. a graph where every edge is an agent pays rent on its own wiring. one thing to know before you scale it. a graph has two return paths, and almost everyone builds one. ↳ the correction edge is short. a gate rejects one unit back to the step that produced it, and it fixes the run you are in ↳ the learning edge is long. an accepted result goes back to the splitter as a constraint, and it fixes every run after skip the second and you get a graph that is fast and never gets smarter. next week it starts from the same place with the same blind spots. and a smaller one that eats whole nights: when a unit fails, return that unit, not the batch. send back four slices because one failed and you have just rewritten three correct ones. do it twice in a run and the run never converges. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Hanako

73,867 просмотров • 1 месяц назад

ANTHROPIC LEAKED A 6-AGENT ASSEMBLY LINE WHERE ONE PROMPT GOES IN AND A FINISHED PR COMES OUT your name shows up in this process exactly once - at the very end, for 5 minutes. prompt → planner → coder → tester → critic → scribe → PR Opus 5 plans once - a bad plan executed by five perfect agents is still a bad result. Sonnet 5 runs 3 parallel lanes - and they only work because the planner made the steps independent. tests loop until green and red goes back to the coder - the critic never sees a broken build. Opus 5 as the critic rejects to the plan, not the code - tests ask "does it run", the critic asks "should it exist". the PR description writes itself from the trace, not from memory - cut this seat and you get 8 PRs nobody can tell apart. one human step in the whole thing: approve or send back - 5 minutes instead of 5 hours. save the setup - 2 models, 6 seats, 2 return paths ↓

ANTHROPIC LEAKED A 6-AGENT ASSEMBLY LINE WHERE ONE PROMPT GOES IN AND A FINISHED PR COMES OUT your name shows up in this process exactly once - at the very end, for 5 minutes. prompt → planner → coder → tester → critic → scribe → PR Opus 5 plans once - a bad plan executed by five perfect agents is still a bad result. Sonnet 5 runs 3 parallel lanes - and they only work because the planner made the steps independent. tests loop until green and red goes back to the coder - the critic never sees a broken build. Opus 5 as the critic rejects to the plan, not the code - tests ask "does it run", the critic asks "should it exist". the PR description writes itself from the trace, not from memory - cut this seat and you get 8 PRs nobody can tell apart. one human step in the whole thing: approve or send back - 5 minutes instead of 5 hours. save the setup - 2 models, 6 seats, 2 return paths ↓

Sprytix

39,283 просмотров • 1 месяц назад

Orchestrators vs. Graphs, clearly explained! orchestrators are great, and everyone builds one first. here is the ceiling: an orchestrator sits above the work and routes every message. five agents report to it. it reads all five. it decides what each one does next, and reads all five replies. that is ten trips through one context, and by the fifth agent that context has read four reports, five instructions and its own reasoning about all of them. Graph engineering fixes this by removing the seat: not a better router, but no router at all. you need both, and here is the sentence that resolves the whole confusion: an orchestrator sits above the work and holds all of it. a graph is the shape of the work, and holds none of it. ↳ above the work: one context that has to see everything before anything ships ↳ inside the work: a splitter that hands out and lets go, and a merge that reads nothing Prompts → Context → Harness → Loops → Graphs the coordination did not disappear. it moved into the edges, where it costs nothing and cannot get tired. the trick is noticing what you actually built. if one node has to see every result before the run can finish, you did not remove the bottleneck. you hired it, gave it the longest context in the system, and made it the thing you were counting on to stay sharp. one thing to know before you scale it. an orchestrator degrades in the one way nothing catches. ↳ it does not crash, time out or return an error. it stays up and keeps routing ↳ it just starts routing worse, somewhere around the fifth report, and every downstream agent does exactly what it was told that last one catches careful people. you can have perfect isolation on every worker and still have one window quietly drifting at the top, and the traces will all look clean because each worker did its job. and the one that eats whole nights: the merge is where this shows up first. ranking five findings is not judgment, it is a sort. if a model is doing it, you are paying a model to read five reports so it can put them in an order that three lines of code would have got right, and now that model has read everything too. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Orchestrators vs. Graphs, clearly explained! orchestrators are great, and everyone builds one first. here is the ceiling: an orchestrator sits above the work and routes every message. five agents report to it. it reads all five. it decides what each one does next, and reads all five replies. that is ten trips through one context, and by the fifth agent that context has read four reports, five instructions and its own reasoning about all of them. Graph engineering fixes this by removing the seat: not a better router, but no router at all. you need both, and here is the sentence that resolves the whole confusion: an orchestrator sits above the work and holds all of it. a graph is the shape of the work, and holds none of it. ↳ above the work: one context that has to see everything before anything ships ↳ inside the work: a splitter that hands out and lets go, and a merge that reads nothing Prompts → Context → Harness → Loops → Graphs the coordination did not disappear. it moved into the edges, where it costs nothing and cannot get tired. the trick is noticing what you actually built. if one node has to see every result before the run can finish, you did not remove the bottleneck. you hired it, gave it the longest context in the system, and made it the thing you were counting on to stay sharp. one thing to know before you scale it. an orchestrator degrades in the one way nothing catches. ↳ it does not crash, time out or return an error. it stays up and keeps routing ↳ it just starts routing worse, somewhere around the fifth report, and every downstream agent does exactly what it was told that last one catches careful people. you can have perfect isolation on every worker and still have one window quietly drifting at the top, and the traces will all look clean because each worker did its job. and the one that eats whole nights: the merge is where this shows up first. ranking five findings is not judgment, it is a sort. if a model is doing it, you are paying a model to read five reports so it can put them in an order that three lines of code would have got right, and now that model has read everything too. below i have quoted my full guide on graph engineering. it covers the three topologies, the verifier patterns, and where the gate should actually open. save this and read it below ↓

Hanako

44,226 просмотров • 20 дней назад

CLAUDE + OBSIDIAN + KARPATHY'S LLM WIKI = A WIKI THAT MAINTAINS ITSELF run this once and your research compounds instead of evaporating sources go in, a wiki comes out, and a loop keeps it honest • three layers, one owner each > the schema - CLAUDE.md, you and the agent co-evolve it > the wiki - markdown the agent owns. it writes, you read > raw sources - immutable, read only, never edited • three operations on repeat > ingest - read the source, write the summary, log one line > query - answer with citations, file it back as a new page > lint - contradictions, orphans and dead links caught early RAG re-derives the same answer from raw chunks on every query. you pay for that thinking again, every time you ask this wiki gets written once and stays current. 10-15 pages per source, nearly 100 sources on the index alone month one it saves you an hour a day. month six it knows your field better than the person you're up against for the senior seat "Obsidian is the IDE, the LLM is the programmer, the wiki is the codebase" - Andrej Karpathy the stack: 📁 Obsidian ↳ 📁 Claude ↳ 📁 Karpathy LLM-Wiki ↳

CLAUDE + OBSIDIAN + KARPATHY'S LLM WIKI = A WIKI THAT MAINTAINS ITSELF run this once and your research compounds instead of evaporating sources go in, a wiki comes out, and a loop keeps it honest • three layers, one owner each > the schema - CLAUDE.md, you and the agent co-evolve it > the wiki - markdown the agent owns. it writes, you read > raw sources - immutable, read only, never edited • three operations on repeat > ingest - read the source, write the summary, log one line > query - answer with citations, file it back as a new page > lint - contradictions, orphans and dead links caught early RAG re-derives the same answer from raw chunks on every query. you pay for that thinking again, every time you ask this wiki gets written once and stays current. 10-15 pages per source, nearly 100 sources on the index alone month one it saves you an hour a day. month six it knows your field better than the person you're up against for the senior seat "Obsidian is the IDE, the LLM is the programmer, the wiki is the codebase" - Andrej Karpathy the stack: 📁 Obsidian ↳ 📁 Claude ↳ 📁 Karpathy LLM-Wiki ↳

Annatar.md

16,939 просмотров • 13 дней назад

ANTHROPIC LEAKED A SETUP WHERE 6 FILES CUT TOKENS BY 84% AND RAISE ACCURACY BY 39% engineers at Google and Microsoft have been running this for a while - they pay $3 where you pay $20. decisions → contracts → dead ends → state → sources → open questions memory moves outside the window - what enters the context is a pointer to a file, not the history. raw history refills the window to 200k every single turn - six pointers take 8k and leave 96% free. same work, same five turns: 1,000,000 tokens against 40,000. decisions written to a file kill the endless "wait, why did we do it this way". written dead ends kill the second lap around the same circle - the agent never walks in there twice. a stable prefix keeps the cache warm - a cache read costs 0.1x of normal input. that's why 20 turns cost 3.15x instead of 20x - one write and nineteen reads. save this and paste it into Claude Code - and your agent stops paying for what it already knew ↓

ANTHROPIC LEAKED A SETUP WHERE 6 FILES CUT TOKENS BY 84% AND RAISE ACCURACY BY 39% engineers at Google and Microsoft have been running this for a while - they pay $3 where you pay $20. decisions → contracts → dead ends → state → sources → open questions memory moves outside the window - what enters the context is a pointer to a file, not the history. raw history refills the window to 200k every single turn - six pointers take 8k and leave 96% free. same work, same five turns: 1,000,000 tokens against 40,000. decisions written to a file kill the endless "wait, why did we do it this way". written dead ends kill the second lap around the same circle - the agent never walks in there twice. a stable prefix keeps the cache warm - a cache read costs 0.1x of normal input. that's why 20 turns cost 3.15x instead of 20x - one write and nineteen reads. save this and paste it into Claude Code - and your agent stops paying for what it already knew ↓

Noisy

137,563 просмотров • 1 месяц назад

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

Yarchi

58,638 просмотров • 4 месяцев назад

I still don't understand why everyone is still running agents in a line. I switched to graphs three weeks ago and my fleet finished in the time my single agent used to spend on step two. what slows every agent system I have seen is not intelligence. it is geometry. and almost nobody is talking about it. one engineer used this to rewrite 535,000 lines of code in 11 days. a manual rewrite of that scale could take close to a year. it cost $165,000 in tokens. the graph was not cheap. it was just faster than a human year. a node is one agent with one job. research one competitor. review one file. check one claim. the moment a node owns two independent jobs you lose the ability to parallelize them cleanly, verify them independently, and debug them in isolation. an edge is a dependency. it only exists when data actually moves across it. everything else is a fake edge. a wait you invented that costs time and produces nothing. find the fake edges and the line collapses into something wider. jobs that can run at the same time run at the same time. what used to take the sum of forty steps now finishes in the time of the slowest layer. the pattern behind every serious agent system looks like a diamond. fan out to gather breadth, one agent per angle, all at once. reduce with plain code, no model tokens spent. verify with a fresh skeptic on every finding. synthesize once from what survived. Claude's own research feature uses a very similar pattern in production. the part nobody warns you about: the verifier needs clean context. give it the same conversation the worker had and it is not checking anything. it is nodding along to itself in a different window. a graph of agents sharing one context is a single loop in a costume. it breaks the same way, just later and more expensively. one rule that holds at every scale. a worker and its verifier must never share a context. your agents are not too slow. they are waiting in a line that did not need to exist. full guide in the article. save it before you build your next agent from scratch.

I still don't understand why everyone is still running agents in a line. I switched to graphs three weeks ago and my fleet finished in the time my single agent used to spend on step two. what slows every agent system I have seen is not intelligence. it is geometry. and almost nobody is talking about it. one engineer used this to rewrite 535,000 lines of code in 11 days. a manual rewrite of that scale could take close to a year. it cost $165,000 in tokens. the graph was not cheap. it was just faster than a human year. a node is one agent with one job. research one competitor. review one file. check one claim. the moment a node owns two independent jobs you lose the ability to parallelize them cleanly, verify them independently, and debug them in isolation. an edge is a dependency. it only exists when data actually moves across it. everything else is a fake edge. a wait you invented that costs time and produces nothing. find the fake edges and the line collapses into something wider. jobs that can run at the same time run at the same time. what used to take the sum of forty steps now finishes in the time of the slowest layer. the pattern behind every serious agent system looks like a diamond. fan out to gather breadth, one agent per angle, all at once. reduce with plain code, no model tokens spent. verify with a fresh skeptic on every finding. synthesize once from what survived. Claude's own research feature uses a very similar pattern in production. the part nobody warns you about: the verifier needs clean context. give it the same conversation the worker had and it is not checking anything. it is nodding along to itself in a different window. a graph of agents sharing one context is a single loop in a costume. it breaks the same way, just later and more expensively. one rule that holds at every scale. a worker and its verifier must never share a context. your agents are not too slow. they are waiting in a line that did not need to exist. full guide in the article. save it before you build your next agent from scratch.

rvaniaaa

257,546 просмотров • 16 дней назад

ANTHROPIC LEAKED A GRAPH WHERE ONE FILE WITH 7 ITEMS CUTS YOUR WORK FROM 8 HOURS TO 40 MINUTES AND TAKES 40 DECISIONS A DAY OFF YOU autonomy isn't a slider you drag to the right - it's a graph with 7 steps, and exactly one edge leads into each one. your approve is worth nothing until there's a description of what the output should be - otherwise you're approving something nobody defined. you can't run a batch without checkpoints, because one crash in the middle rolls back all 40 tasks at once. the agent already works without you, and until it writes down what it did there's nothing to check the report against. this is where the point of no return sits: past it the loop runs while you sleep. the approval didn't disappear - you moved it onto an evaluator that never gets tired and never lets one through. silence is only allowed when there's a list of what breaks it: money, deletion, anything leaving the system. the last one is the brake - a turn limit and a budget cap, whichever runs out first kills the run. you build the brake before the engine - an agent you can't stop isn't autonomous, it's just unattended. skip one edge and nothing crashes and nobody warns you - the system quietly settles two steps lower and keeps running. save this - 7 steps, 7 artefacts, zero ways to jump one ↓

ANTHROPIC LEAKED A GRAPH WHERE ONE FILE WITH 7 ITEMS CUTS YOUR WORK FROM 8 HOURS TO 40 MINUTES AND TAKES 40 DECISIONS A DAY OFF YOU autonomy isn't a slider you drag to the right - it's a graph with 7 steps, and exactly one edge leads into each one. your approve is worth nothing until there's a description of what the output should be - otherwise you're approving something nobody defined. you can't run a batch without checkpoints, because one crash in the middle rolls back all 40 tasks at once. the agent already works without you, and until it writes down what it did there's nothing to check the report against. this is where the point of no return sits: past it the loop runs while you sleep. the approval didn't disappear - you moved it onto an evaluator that never gets tired and never lets one through. silence is only allowed when there's a list of what breaks it: money, deletion, anything leaving the system. the last one is the brake - a turn limit and a budget cap, whichever runs out first kills the run. you build the brake before the engine - an agent you can't stop isn't autonomous, it's just unattended. skip one edge and nothing crashes and nobody warns you - the system quietly settles two steps lower and keeps running. save this - 7 steps, 7 artefacts, zero ways to jump one ↓

Sprytix

41,920 просмотров • 1 месяц назад

Introducing Gateway. Your agent needs to check a payment. You hand it a key that can also refund it. It needs to draft a page. That key can archive every page. Not anymore. Gateway gives every agent one key with only the tools you grant. MCP servers and your own APIs, same key. Change the grant when the job changes. The agent never sees your real credentials. Beta customers already run over 95,000 calls each through it. Watch it work ↓

Introducing Gateway. Your agent needs to check a payment. You hand it a key that can also refund it. It needs to draft a page. That key can archive every page. Not anymore. Gateway gives every agent one key with only the tools you grant. MCP servers and your own APIs, same key. Change the grant when the job changes. The agent never sees your real credentials. Beta customers already run over 95,000 calls each through it. Watch it work ↓

mem0

34,068 просмотров • 20 дней назад

ANTHROPIC LEAKED A FILE WHERE 5 AGENTS WITH JEV BUILD A $1.2M A YEAR SYSTEM IN 30 MINUTES you pay $3.70 and walk away with an asset that can do $1.2M a year repo → data model → API → UI → evals no layer starts until the one under it is closed, and that edge is what turns five scripts into a system the operator on Haiku 4.5 brings up the repo and CI, the architect on Opus 5 lays down the data model and migrations two builders on Sonnet 5 run API and UI in parallel, and the reviewer on Opus 5.5 can keep finished code out of prod the evals were sitting in the file before the first line of code existed at minute zero there was not a single file, by the end it is a working product with payments and tests five agents cover in half an hour what a human team bills for a quarter JEV hands one line between layers instead of the whole history, so the next agent never re-reads the project and the run costs $3.70 instead of $370 the build takes 30 minutes, the first customers show up weeks later save this and paste it into Claude Code - let it assemble those 5 layers for you ↓

ANTHROPIC LEAKED A FILE WHERE 5 AGENTS WITH JEV BUILD A $1.2M A YEAR SYSTEM IN 30 MINUTES you pay $3.70 and walk away with an asset that can do $1.2M a year repo → data model → API → UI → evals no layer starts until the one under it is closed, and that edge is what turns five scripts into a system the operator on Haiku 4.5 brings up the repo and CI, the architect on Opus 5 lays down the data model and migrations two builders on Sonnet 5 run API and UI in parallel, and the reviewer on Opus 5.5 can keep finished code out of prod the evals were sitting in the file before the first line of code existed at minute zero there was not a single file, by the end it is a working product with payments and tests five agents cover in half an hour what a human team bills for a quarter JEV hands one line between layers instead of the whole history, so the next agent never re-reads the project and the run costs $3.70 instead of $370 the build takes 30 minutes, the first customers show up weeks later save this and paste it into Claude Code - let it assemble those 5 layers for you ↓

Sprytix

14,208 просмотров • 9 дней назад

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

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

153,908 просмотров • 3 месяцев назад

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

GREG ISENBERG

194,524 просмотров • 5 месяцев назад

ANTHROPIC LEAKED A $3.4M FILE THAT GIVES YOU A $120K/MONTH ENGINEERING TEAM IN 10 MINUTES AND BUILDS ANY SYSTEM Microsoft and Google have been using this file for a while - 5 roles, zero hires, and it costs $0. in 10 minutes the whole system is up: core, skills, contracts, tests, cron and a team already working. all of it rests on the root you write: who buys, what it costs, what the team never does, and one metric. Sonnet 5 brings up the core and wires the skills, Opus 5 splits the task and judges the result, Haiku 4.5 assembles the report on the batch queue. contracts get written before the workers - without them every hop re-guesses what the last one meant. with contracts the same object travels between all 5 roles: SETUP.md → skeleton → task graph → gate → report. the critic is the gate - nothing ships past it, which is why you never get a green build with dead logic. the auditor writes one line back into the root - tomorrow's team is better than today's, and you opened nothing. without that edge you don't have a loop, you have 5 scripts repeating monday for a year. 4 typed handoffs and 1 return - the whole system rests on those five arrows. save this and paste it into Claude Code - 10 minutes, 5 roles, zero hires ↓

ANTHROPIC LEAKED A $3.4M FILE THAT GIVES YOU A $120K/MONTH ENGINEERING TEAM IN 10 MINUTES AND BUILDS ANY SYSTEM Microsoft and Google have been using this file for a while - 5 roles, zero hires, and it costs $0. in 10 minutes the whole system is up: core, skills, contracts, tests, cron and a team already working. all of it rests on the root you write: who buys, what it costs, what the team never does, and one metric. Sonnet 5 brings up the core and wires the skills, Opus 5 splits the task and judges the result, Haiku 4.5 assembles the report on the batch queue. contracts get written before the workers - without them every hop re-guesses what the last one meant. with contracts the same object travels between all 5 roles: SETUP.md → skeleton → task graph → gate → report. the critic is the gate - nothing ships past it, which is why you never get a green build with dead logic. the auditor writes one line back into the root - tomorrow's team is better than today's, and you opened nothing. without that edge you don't have a loop, you have 5 scripts repeating monday for a year. 4 typed handoffs and 1 return - the whole system rests on those five arrows. save this and paste it into Claude Code - 10 minutes, 5 roles, zero hires ↓

Noisy

19,483 просмотров • 1 месяц назад