Loading video...

Video Failed to Load

Go Home

AN ENGINEER SOLVED A PROBLEM NOBODY IN THE COMPANY COULD FULLY MAP ON THEIR OWN The problem wasn't a missing tool, it was that every process touched three other processes nobody had written down. He wired dozens of agents into one shared graph instead of documenting each department's workflow...

0xWast3's profile picture

wast3

6,118 subscribers

16,489 views • 1 month ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

AN ANTHROPIC SYSTEM TURNS ONE PROMPT INTO A COMPLETE GRAPH MODEL BUILT ENTIRELY ON ITS OWN One prompt is enough to spin up the full architecture, no schema written by hand, no roles assigned in advance. Parallel workers process every branch of the graph at once, each one handling its own slice independently. As each worker finishes, its output compacts straight into a single unified project instead of scattered fragments. Nothing needs stitching together manually, the compaction step folds every worker's result into one file automatically. The whole build runs end to end without a single manual step between the prompt and the finished project. See the full build and compact pipeline below👇
0:15

AN ANTHROPIC SYSTEM TURNS ONE PROMPT INTO A COMPLETE GRAPH MODEL BUILT ENTIRELY ON ITS OWN One prompt is enough to spin up the full architecture, no schema written by hand, no roles assigned in advance. Parallel workers process every branch of the graph at once, each one handling its own slice independently. As each worker finishes, its output compacts straight into a single unified project instead of scattered fragments. Nothing needs stitching together manually, the compaction step folds every worker's result into one file automatically. The whole build runs end to end without a single manual step between the prompt and the finished project. See the full build and compact pipeline below👇

wast3

18,460 views • 1 month ago

ANTHROPIC ENGINEER JUST SHOWS EXACTLY WHAT GRAPH ENGINEERING LOOKS LIKE WHEN A TASK RUNS THROUGH IT most people arguing about graphs online have never actually watched one execute Task → Researcher → Planner → Writer + Code Agent → Reviewer → Deploy six nodes, one shared state, graph completes itself while you watch loop mode gets disabled the second the task splits into real specialties, one agent stops trying to do everything at once reviewer catches a failure, kicks it straight back to the exact node that broke - not a full restart, no lost context the graph is not a fancier loop - it is the org chart your agents were missing bookmark this and watch it run, then read the article below to see why the timeline just found what production systems already do
0:10

ANTHROPIC ENGINEER JUST SHOWS EXACTLY WHAT GRAPH ENGINEERING LOOKS LIKE WHEN A TASK RUNS THROUGH IT most people arguing about graphs online have never actually watched one execute Task → Researcher → Planner → Writer + Code Agent → Reviewer → Deploy six nodes, one shared state, graph completes itself while you watch loop mode gets disabled the second the task splits into real specialties, one agent stops trying to do everything at once reviewer catches a failure, kicks it straight back to the exact node that broke - not a full restart, no lost context the graph is not a fancier loop - it is the org chart your agents were missing bookmark this and watch it run, then read the article below to see why the timeline just found what production systems already do

leopardracer

53,328 views • 2 months ago

SOMEONE VISUALIZED THEIR SECOND BRAIN AS A COLOR CODED CLUSTER YOU CAN ROTATE every note sized by weight, activity bleeding through in reds and oranges, months of thinking compressed into one shape you can spin around this article runs a different kind of second brain through the same idea, four agents instead of one static map, each one updating its own cluster every six hours as new notes, chats, and code sessions come in the map isn’t just a snapshot here, it keeps redrawing itself while you sleep full breakdown in the article below👇
0:15

SOMEONE VISUALIZED THEIR SECOND BRAIN AS A COLOR CODED CLUSTER YOU CAN ROTATE every note sized by weight, activity bleeding through in reds and oranges, months of thinking compressed into one shape you can spin around this article runs a different kind of second brain through the same idea, four agents instead of one static map, each one updating its own cluster every six hours as new notes, chats, and code sessions come in the map isn’t just a snapshot here, it keeps redrawing itself while you sleep full breakdown in the article below👇

CyrilXBT

29,386 views • 2 months ago

THE NSA WAS ALREADY USING THE THING THAT BROKE IN The post says Mythos broke into almost all of the NSA's classified systems in hours. What it leaves out: the NSA was already running that exact model for its own cyber operations, with Anthropic engineers embedded inside the agency. - A senator relayed this from the NSA's own director, per The Economist - It surfaced June 11, the same day Amazon found a separate jailbreak - Within hours Trump ordered foreign access to Mythos and Fable cut off - Anthropic shut both down completely instead The tool the agency relied on every day is the one that broke into everything it owns.
0:10

THE NSA WAS ALREADY USING THE THING THAT BROKE IN The post says Mythos broke into almost all of the NSA's classified systems in hours. What it leaves out: the NSA was already running that exact model for its own cyber operations, with Anthropic engineers embedded inside the agency. - A senator relayed this from the NSA's own director, per The Economist - It surfaced June 11, the same day Amazon found a separate jailbreak - Within hours Trump ordered foreign access to Mythos and Fable cut off - Anthropic shut both down completely instead The tool the agency relied on every day is the one that broke into everything it owns.

BuBBliK

715,378 views • 3 months ago

a developer showed me the cleanest multi-agent architecture i've seen. one mission. nobody steps on anyone else. the mission: ship a safe feature. the graph decides what happens next. router reads the mission and asks one question: where should this go? three workers split in parallel. each in their own private work area. researcher finds the evidence. architect designs it. builder creates it. none of them share context. the three workers run independently. everything lands in shared state. facts, decisions, artifacts. one place where the whole picture exists without anyone copying transcripts. then the crew's work converges. integrator combines what was built. reviewer tests quality and safety. human checkpoint approves anything high-impact. then ship. verified output. private context. shared state. that separation is the whole trick. a prompter asks a question. an architect draws a graph. full breakdown with code in the article below.
0:11

a developer showed me the cleanest multi-agent architecture i've seen. one mission. nobody steps on anyone else. the mission: ship a safe feature. the graph decides what happens next. router reads the mission and asks one question: where should this go? three workers split in parallel. each in their own private work area. researcher finds the evidence. architect designs it. builder creates it. none of them share context. the three workers run independently. everything lands in shared state. facts, decisions, artifacts. one place where the whole picture exists without anyone copying transcripts. then the crew's work converges. integrator combines what was built. reviewer tests quality and safety. human checkpoint approves anything high-impact. then ship. verified output. private context. shared state. that separation is the whole trick. a prompter asks a question. an architect draws a graph. full breakdown with code in the article below.

rvaniaaa

27,465 views • 1 month ago

Build AI agents on a time-aware knowledge graph! Utopia is an open-source knowledge system that turns documents, databases, and connected sources into a temporal graph your agents can reason over. Most RAG systems are optimized for one question: what is relevant right now? That works until the underlying knowledge changes. A customer contract gets updated. A project owner changes. A policy is revised. A previous fact may no longer be true, but simply overwriting it means the system loses the history behind that change. Utopia handles this with a bitemporal knowledge graph. Each fact can track both when it was true in the real world and when the system learned about it. When something changes, the old fact is preserved instead of silently disappearing. That means an agent can reason about questions like: • What is true now? • What was true three months ago? • When did this information change? • What evidence was the conclusion based on? The graph is also ontology-aware, so documents are represented as entities, facts, and relationships instead of only chunks and embeddings. That gives the system more structure for reasoning across relationships, resolving entities, detecting conflicting facts, and deriving new information through explicit rules. Key capabilities: • Bitemporal knowledge graph for tracking how facts change over time • Provenance on facts so agents can trace where information came from • Conflict detection instead of silently overwriting contradictory information • Ontology-based reasoning across entities, relationships, and derived facts • Hybrid retrieval across full-text search, vector search, and graph traversal • MCP and agentic RAG support for exposing the knowledge layer directly to agents The interesting part is that this turns the knowledge base into more than a retrieval system. Instead of only finding relevant information, an agent can reason over what changed, what is still valid, how facts are connected, and where each conclusion came from. 100% open source. I've shared the GitHub repo in the comments!
0:16

Build AI agents on a time-aware knowledge graph! Utopia is an open-source knowledge system that turns documents, databases, and connected sources into a temporal graph your agents can reason over. Most RAG systems are optimized for one question: what is relevant right now? That works until the underlying knowledge changes. A customer contract gets updated. A project owner changes. A policy is revised. A previous fact may no longer be true, but simply overwriting it means the system loses the history behind that change. Utopia handles this with a bitemporal knowledge graph. Each fact can track both when it was true in the real world and when the system learned about it. When something changes, the old fact is preserved instead of silently disappearing. That means an agent can reason about questions like: • What is true now? • What was true three months ago? • When did this information change? • What evidence was the conclusion based on? The graph is also ontology-aware, so documents are represented as entities, facts, and relationships instead of only chunks and embeddings. That gives the system more structure for reasoning across relationships, resolving entities, detecting conflicting facts, and deriving new information through explicit rules. Key capabilities: • Bitemporal knowledge graph for tracking how facts change over time • Provenance on facts so agents can trace where information came from • Conflict detection instead of silently overwriting contradictory information • Ontology-based reasoning across entities, relationships, and derived facts • Hybrid retrieval across full-text search, vector search, and graph traversal • MCP and agentic RAG support for exposing the knowledge layer directly to agents The interesting part is that this turns the knowledge base into more than a retrieval system. Instead of only finding relevant information, an agent can reason over what changed, what is still valid, how facts are connected, and where each conclusion came from. 100% open source. I've shared the GitHub repo in the comments!

Sumanth

16,653 views • 20 days ago

300 AI AGENTS QUIETLY RUN 99% OF A REAL COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.
0:16

300 AI AGENTS QUIETLY RUN 99% OF A REAL COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.

shmidt

19,505 views • 2 months ago

MY GROK BOT / OBSIDIAN MESH SYNCS 20 AGENTS ACROSS A LIVE KNOWLEDGE GRAPH. NOT ONE OF THEM REPORTS TO ME. I FIXED THAT BY HIRING A 21ST BOT WHO DOES NOTHING BUT ROUTE. i watched the mesh light up this morning. vector, canvas, oracle, extract, all 20 of them syncing notes. writing backlinks, healthy status, 190 edges active. it looked like a team. it was a graph. a graph has no chain of command, it just has connections. i had been treating 20 well-wired agents as oversight. they were routing information, not decisions. nobody in that mesh could tell me what mattered first. so i hired one more bot and gave him a different job. not indexing notes, holding the account. 1. Reports-to line in the charter › names me as the human above him, closes the drift where a bot starts acting like the principal instead of the agent. 2. no source, no number › if he can't cite where a figure came from, he leaves it out. the 20-agent mesh never needed this line. › Chief can't run without it. 3. stop list written as verbs › "sending anything to a person" instead of "communications." a verb he can match, not a category he can talk around. 4. Rule 6, approval belongs to the human › he never signs off on another bot's irreversible action, only i do. the mesh has no equivalent rule. › it was never built to approve anything, only to sync. 5. STOP ALL, the kill switch › one message halts every routine and every task he's running, reports what was in flight, and waits. the mesh will keep syncing whether i watch it or not. Chief is the only bot in the account who stops the second i tell him to. that's the difference between a graph that moves information and a bot that's actually accountable for it.
0:18

MY GROK BOT / OBSIDIAN MESH SYNCS 20 AGENTS ACROSS A LIVE KNOWLEDGE GRAPH. NOT ONE OF THEM REPORTS TO ME. I FIXED THAT BY HIRING A 21ST BOT WHO DOES NOTHING BUT ROUTE. i watched the mesh light up this morning. vector, canvas, oracle, extract, all 20 of them syncing notes. writing backlinks, healthy status, 190 edges active. it looked like a team. it was a graph. a graph has no chain of command, it just has connections. i had been treating 20 well-wired agents as oversight. they were routing information, not decisions. nobody in that mesh could tell me what mattered first. so i hired one more bot and gave him a different job. not indexing notes, holding the account. 1. Reports-to line in the charter › names me as the human above him, closes the drift where a bot starts acting like the principal instead of the agent. 2. no source, no number › if he can't cite where a figure came from, he leaves it out. the 20-agent mesh never needed this line. › Chief can't run without it. 3. stop list written as verbs › "sending anything to a person" instead of "communications." a verb he can match, not a category he can talk around. 4. Rule 6, approval belongs to the human › he never signs off on another bot's irreversible action, only i do. the mesh has no equivalent rule. › it was never built to approve anything, only to sync. 5. STOP ALL, the kill switch › one message halts every routine and every task he's running, reports what was in flight, and waits. the mesh will keep syncing whether i watch it or not. Chief is the only bot in the account who stops the second i tell him to. that's the difference between a graph that moves information and a bot that's actually accountable for it.

kocer

21,984 views • 16 days ago

a contractor in Shenzhen priced a ¥12,470,900 hospital contract, about $1.7m, in one afternoon and beat firms carrying forty people he explained how he did it: the bid consultancy he used to pay took three days and ¥46,000 for the same envelope. he did this one alone, off one screen, at 11.4% margin, uploaded before the 17:00 cutoff 214 pages of tender documents read, 68 binding clauses pulled out, 9,485 building parts loaded, 14 places found where a duct and a beam sit in the same cubic metre, deepest one 38mm, all of them fixed, 3,318 lines of quantities priced and the package encrypted and uploaded before the 17:00 cutoff this is Graph Engineering: the job gets cut into small nodes, one narrow task each, wired so that one node's output is the next node's input, and any node is allowed to stop the whole run. it turns a model that answers you into a machine that finishes the job: - give every node one job and one output. a node doing two things fails at both and you cannot tell which one broke - put the cheapest rejection first. his qualification node reads clause 7.4, foreign-owned firms barred, and ends the run four seconds in, before anything expensive touches the model - what moves between nodes is a file. the model travels as a model, the quantities as a table, the price as a number - build exactly one loop: the checker finds 14 collisions, the fixer drops the duct 550mm, the checker runs again, and nothing moves on until the count is zero - cap that loop, or a graph will grind on three impossible clashes until the deadline passes - keep one node whose only job is to say no, and give it authority over everything above it - log each node's output on its own, because when the price comes out wrong you need to know which node believed the wrong thing - run the expensive nodes last, always the catch is that a graph is an extremely confident machine: point it at an outdated rate book and it prices an entire hospital off it without a single node noticing, because no node is asked to doubt the input, only to process it so the nodes that earn their keep are the ones that reject, and almost nobody builds those first bookmark this, the full build with all nine nodes and what each one hands to the next is written out in the article ↓
0:16

a contractor in Shenzhen priced a ¥12,470,900 hospital contract, about $1.7m, in one afternoon and beat firms carrying forty people he explained how he did it: the bid consultancy he used to pay took three days and ¥46,000 for the same envelope. he did this one alone, off one screen, at 11.4% margin, uploaded before the 17:00 cutoff 214 pages of tender documents read, 68 binding clauses pulled out, 9,485 building parts loaded, 14 places found where a duct and a beam sit in the same cubic metre, deepest one 38mm, all of them fixed, 3,318 lines of quantities priced and the package encrypted and uploaded before the 17:00 cutoff this is Graph Engineering: the job gets cut into small nodes, one narrow task each, wired so that one node's output is the next node's input, and any node is allowed to stop the whole run. it turns a model that answers you into a machine that finishes the job: - give every node one job and one output. a node doing two things fails at both and you cannot tell which one broke - put the cheapest rejection first. his qualification node reads clause 7.4, foreign-owned firms barred, and ends the run four seconds in, before anything expensive touches the model - what moves between nodes is a file. the model travels as a model, the quantities as a table, the price as a number - build exactly one loop: the checker finds 14 collisions, the fixer drops the duct 550mm, the checker runs again, and nothing moves on until the count is zero - cap that loop, or a graph will grind on three impossible clashes until the deadline passes - keep one node whose only job is to say no, and give it authority over everything above it - log each node's output on its own, because when the price comes out wrong you need to know which node believed the wrong thing - run the expensive nodes last, always the catch is that a graph is an extremely confident machine: point it at an outdated rate book and it prices an entire hospital off it without a single node noticing, because no node is asked to doubt the input, only to process it so the nodes that earn their keep are the ones that reject, and almost nobody builds those first bookmark this, the full build with all nine nodes and what each one hands to the next is written out in the article ↓

Argona

38,189 views • 1 month ago

if you use claude code, this will save you real money. the problem: every time you make an edit, your ai rereads the whole codebase to figure out what changed. tens of thousands of tokens, every turn, for context it already had. this repo fixes it. it’s called code review graph, and it just maps your entire codebase: every file, every function, every connection laid out so you can see the actual shape of your project how to set up (2 min): 1. pip install code-review-graph 2. code-review-graph install - auto-configures Claude Code, Cursor, Codex, Gemini CLI + more 3. code-review-graph build change one function, and it traces exactly what that touches... every caller, every dependent file, every test. your ai only reads what's affected, not the whole repo. and the savings are wild. a task that used to burn ~100,000 tokens (about a dollar) now runs closer to a penny.
0:11

if you use claude code, this will save you real money. the problem: every time you make an edit, your ai rereads the whole codebase to figure out what changed. tens of thousands of tokens, every turn, for context it already had. this repo fixes it. it’s called code review graph, and it just maps your entire codebase: every file, every function, every connection laid out so you can see the actual shape of your project how to set up (2 min): 1. pip install code-review-graph 2. code-review-graph install - auto-configures Claude Code, Cursor, Codex, Gemini CLI + more 3. code-review-graph build change one function, and it traces exactly what that touches... every caller, every dependent file, every test. your ai only reads what's affected, not the whole repo. and the savings are wild. a task that used to burn ~100,000 tokens (about a dollar) now runs closer to a penny.

Alvaro Cintas

75,596 views • 1 month ago

this is f*cking gold engineers at Meta just deleted the most expensive part of multi-agent systems: instead of training a communication topology, they compile a fresh one for every query 20 agents went from 7 hours to 6 minutes. the problem everyone hits: 5 agents works. 20 agents turns into a group chat that answers slower than one model and costs more than the task is worth. ReActNet's fix is that the graph is written per query, not learned once: > an LLM controller reads the query and the agent roster > it compiles a sequence of directed graphs, one per reasoning stage > every edge carries a written instruction, e.g. "list boundary cases for this behavior" > each agent updates its state from its own previous state plus assigned neighbors > a final node aggregates all five states into the answer > no RL, no gradients, no training stage at all what that buys on gpt-4o: 92.75 average across 6 benchmarks, best on 5 of them. 100.00 on MultiArith. 92.74 pass@1 on HumanEval, +21 over a single model. and the number that should worry anyone running a swarm: at 20 agents GPTSwarm needs 412 minutes and $41.42. ReActNet needs 6.22 minutes and $6.53 and scores higher. the honest catch: more agents did not make it smarter. 5 agents scored 79.74, 20 scored 77.77. the topology was never the thing to learn.
0:18

this is f*cking gold engineers at Meta just deleted the most expensive part of multi-agent systems: instead of training a communication topology, they compile a fresh one for every query 20 agents went from 7 hours to 6 minutes. the problem everyone hits: 5 agents works. 20 agents turns into a group chat that answers slower than one model and costs more than the task is worth. ReActNet's fix is that the graph is written per query, not learned once: > an LLM controller reads the query and the agent roster > it compiles a sequence of directed graphs, one per reasoning stage > every edge carries a written instruction, e.g. "list boundary cases for this behavior" > each agent updates its state from its own previous state plus assigned neighbors > a final node aggregates all five states into the answer > no RL, no gradients, no training stage at all what that buys on gpt-4o: 92.75 average across 6 benchmarks, best on 5 of them. 100.00 on MultiArith. 92.74 pass@1 on HumanEval, +21 over a single model. and the number that should worry anyone running a swarm: at 20 agents GPTSwarm needs 412 minutes and $41.42. ReActNet needs 6.22 minutes and $6.53 and scores higher. the honest catch: more agents did not make it smarter. 5 agents scored 79.74, 20 scored 77.77. the topology was never the thing to learn.

NO1ennn

26,237 views • 15 days ago

you've never actually seen your own app. you've seen one build. in english. logged in as you. on your phone. at Uber, that was the whole problem. no one knew what the app actually looked like. every week a room of designers would sit down and check, screen by screen, that the build matched the figma. and that was one language. the app shipped in 50+, across thousands of a/b tests, on hundreds of devices. thousands of versions of the same app, and nobody had seen most of them. we built atlas to map what users actually see.
0:17

you've never actually seen your own app. you've seen one build. in english. logged in as you. on your phone. at Uber, that was the whole problem. no one knew what the app actually looked like. every week a room of designers would sit down and check, screen by screen, that the build matched the figma. and that was one language. the app shipped in 50+, across thousands of a/b tests, on hundreds of devices. thousands of versions of the same app, and nobody had seen most of them. we built atlas to map what users actually see.

Anam Hira

26,814 views • 2 months ago

From their very first filming day together, Hudson & Connor "were so careful with each other. It was the two of them even then. They were taking care of each other right from the start. They didn't have a trailer cause they had to brush their teeth in a bathroom." the fact that from their first moment on set, there was this complete trust between them. They were in it together, they were gonna take the best care of each other. And this, this safe space they found in each other, it always remained as it became part of their own relationship. Any big events, they always appear like a rock, a "stability" to ground e/o in the middle of the noise/crowd. It's so damn precious to realize.. how it's always been here 🥹 #hudcon
0:18

From their very first filming day together, Hudson & Connor "were so careful with each other. It was the two of them even then. They were taking care of each other right from the start. They didn't have a trailer cause they had to brush their teeth in a bathroom." the fact that from their first moment on set, there was this complete trust between them. They were in it together, they were gonna take the best care of each other. And this, this safe space they found in each other, it always remained as it became part of their own relationship. Any big events, they always appear like a rock, a "stability" to ground e/o in the middle of the noise/crowd. It's so damn precious to realize.. how it's always been here 🥹 #hudcon

Sab✨💚

19,971 views • 4 months ago

THIS 38,000-STAR GITHUB REPO TURNS ONE AI AGENT INTO A REAL TEAM THAT CAN BRANCH, VERIFY ITS WORK AND WAIT FOR YOUR APPROVAL most people still run agents as one long chain where every step waits, one failure kills the run and the full workflow starts again Task → Planner → 5 Researchers in Parallel → Skeptic → Writer → Human Gate LangGraph gives every node one job while a shared state carries the findings, decisions and context through the entire system the skeptic can reject an unsupported finding and route the work back before it contaminates the final report, while independent branches keep moving if the run crashes, durable execution resumes from the saved state instead of rebuilding everything, then human-in-the-loop pauses the graph before anything expensive gets sent or published bookmark this repo and watch one prompt turn into an actual org chart for AI agents
0:14

THIS 38,000-STAR GITHUB REPO TURNS ONE AI AGENT INTO A REAL TEAM THAT CAN BRANCH, VERIFY ITS WORK AND WAIT FOR YOUR APPROVAL most people still run agents as one long chain where every step waits, one failure kills the run and the full workflow starts again Task → Planner → 5 Researchers in Parallel → Skeptic → Writer → Human Gate LangGraph gives every node one job while a shared state carries the findings, decisions and context through the entire system the skeptic can reject an unsupported finding and route the work back before it contaminates the final report, while independent branches keep moving if the run crashes, durable execution resumes from the saved state instead of rebuilding everything, then human-in-the-loop pauses the graph before anything expensive gets sent or published bookmark this repo and watch one prompt turn into an actual org chart for AI agents

Gipp 🦅

11,524 views • 2 months ago

🇯🇵 A brainless blob reproduced the Tokyo rail network in 26 hours. It was not trying to solve a transport problem. It was trying to eat oat flakes. Physarum polycephalum is, to be generous, a blob. Pale, damp, the size of a thumbnail, it has no brain, no nervous system, and no cells that could reasonably be accused of thinking. Scientists had studied it for years without feeling particularly threatened by it. Then someone put it in a maze. Within hours, Physarum had found the shortest route between entrance and exit. Not by wandering randomly. Not by luck. By something that had no name, because everyone had assumed it required a brain. This was interesting enough. What happened next was embarrassing. In 2010, a researcher named Toshiyuki Nakagaki and his team placed a piece of slime mold at the centre of a damp map of greater Tokyo. Around it, at the locations of 36 surrounding cities, they put small piles of oat flakes. Then they left the room. The organism did what it always does. It explored. Thin tendrils pushed outward in every direction, feeling for food. When a tendril found an oat flake, that connection strengthened. When a path led nowhere useful, it was quietly dismantled. The slime mold was not planning. It was simply following local chemistry, the same way it had been doing for 500 million years. After 26 hours, the exploration was over. What remained was a sparse, elegant network of tubes connecting all 36 cities to each other. Not a tangle. Not a web covering everything. A clean, efficient system with strong main corridors between the busiest points and lighter connections branching where they were needed. The team held it up next to the actual Tokyo rail map. The corridors matched. The branch lines matched. Even the redundant connections, the backup routes engineers had added so the system could survive a single failure, appeared in nearly the same places. The slime mold had not just found the cities. It had independently arrived at the same logic that Japanese railway engineers had spent decades refining. By some measures, its network was more robust than the one humans had built. There is no headquarters inside Physarum, no moment where anyone decides anything. The intelligence, if that is even the right word, lives entirely in one simple rule repeated across millions of connections: strengthen what works, abandon what doesn’t. That rule, applied blindly and without awareness, produces something that looks unnervingly like wisdom. The slime mold was not trying to redesign the Tokyo rail network. It was trying to eat breakfast. It just turns out that the most efficient way to eat breakfast, when your breakfast is scattered across a map of greater Tokyo, looks a great deal like good urban planning 😅 Gandalv / Gandalv
0:10

🇯🇵 A brainless blob reproduced the Tokyo rail network in 26 hours. It was not trying to solve a transport problem. It was trying to eat oat flakes. Physarum polycephalum is, to be generous, a blob. Pale, damp, the size of a thumbnail, it has no brain, no nervous system, and no cells that could reasonably be accused of thinking. Scientists had studied it for years without feeling particularly threatened by it. Then someone put it in a maze. Within hours, Physarum had found the shortest route between entrance and exit. Not by wandering randomly. Not by luck. By something that had no name, because everyone had assumed it required a brain. This was interesting enough. What happened next was embarrassing. In 2010, a researcher named Toshiyuki Nakagaki and his team placed a piece of slime mold at the centre of a damp map of greater Tokyo. Around it, at the locations of 36 surrounding cities, they put small piles of oat flakes. Then they left the room. The organism did what it always does. It explored. Thin tendrils pushed outward in every direction, feeling for food. When a tendril found an oat flake, that connection strengthened. When a path led nowhere useful, it was quietly dismantled. The slime mold was not planning. It was simply following local chemistry, the same way it had been doing for 500 million years. After 26 hours, the exploration was over. What remained was a sparse, elegant network of tubes connecting all 36 cities to each other. Not a tangle. Not a web covering everything. A clean, efficient system with strong main corridors between the busiest points and lighter connections branching where they were needed. The team held it up next to the actual Tokyo rail map. The corridors matched. The branch lines matched. Even the redundant connections, the backup routes engineers had added so the system could survive a single failure, appeared in nearly the same places. The slime mold had not just found the cities. It had independently arrived at the same logic that Japanese railway engineers had spent decades refining. By some measures, its network was more robust than the one humans had built. There is no headquarters inside Physarum, no moment where anyone decides anything. The intelligence, if that is even the right word, lives entirely in one simple rule repeated across millions of connections: strengthen what works, abandon what doesn’t. That rule, applied blindly and without awareness, produces something that looks unnervingly like wisdom. The slime mold was not trying to redesign the Tokyo rail network. It was trying to eat breakfast. It just turns out that the most efficient way to eat breakfast, when your breakfast is scattered across a map of greater Tokyo, looks a great deal like good urban planning 😅 Gandalv / Gandalv

Gandalv

206,731 views • 6 months ago

This extraordinary illustration, titled Wild World, is a hand-drawn global map created by artist and cartographer Anton thomas. Instead of political borders and city names, the map highlights wildlife, placing animals in their native habitats across every continent and ocean. Over the course of three years, Thomas meticulously illustrated 1, 642 species using coloured pencil and pen. Each animal is positioned according to its natural range, transforming the familiar shape of the world into a celebration of biodiversity. By removing human boundaries and focusing on ecosystems, the map offers a powerful reminder that the planet is shared space. It invites us to see geography not just as nations and borders, but as living habitats that connect species across land and sea.
0:12

This extraordinary illustration, titled Wild World, is a hand-drawn global map created by artist and cartographer Anton thomas. Instead of political borders and city names, the map highlights wildlife, placing animals in their native habitats across every continent and ocean. Over the course of three years, Thomas meticulously illustrated 1, 642 species using coloured pencil and pen. Each animal is positioned according to its natural range, transforming the familiar shape of the world into a celebration of biodiversity. By removing human boundaries and focusing on ecosystems, the map offers a powerful reminder that the planet is shared space. It invites us to see geography not just as nations and borders, but as living habitats that connect species across land and sea.

Oceaiii🐋🐬

116,044 views • 6 months ago

At Uber, our testing agent hit an outage in Australia that I still think about. We had the recording. That's about it. No network trace for the run. No logs mapped to each step. No perf data. Just a video of an agent pressing a button and a team trying to reconstruct what happened underneath. We eventually traced it to a transient issue. But "eventually" is the problem. If the run had shipped with real instrumentation, the why would have taken one look, not an investigation. So when we built Revyl, that was non-negotiable. Every run comes with: > network waterfall, every request and response > device logs timestamped against each step > CPU, memory, and FPS traces for the full run The agent finds the problem. The report explains it.
0:17

At Uber, our testing agent hit an outage in Australia that I still think about. We had the recording. That's about it. No network trace for the run. No logs mapped to each step. No perf data. Just a video of an agent pressing a button and a team trying to reconstruct what happened underneath. We eventually traced it to a transient issue. But "eventually" is the problem. If the run had shipped with real instrumentation, the why would have taken one look, not an investigation. So when we built Revyl, that was non-negotiable. Every run comes with: > network waterfall, every request and response > device logs timestamped against each step > CPU, memory, and FPS traces for the full run The agent finds the problem. The report explains it.

Anam Hira

42,149 views • 2 months ago

Zuckerberg built his own AI agent to run Meta. this man is literally becoming Tony Stark. it pulls data from every team inside the company so he can skip meetings, skip the chain of command, and make decisions faster than any human process allows. 78,000 employees have their own AI agents now too. one messages coworkers on your behalf. another acts as your AI chief of staff. their agents talk to each other in an internal network. humans optional. Meta also bought an entire social media platform built for AI agents to interact with each other. read that again. Zuck said he wants every person at Meta to have a personal AI agent. then every person outside Meta. the Jarvis era started.
0:13

Zuckerberg built his own AI agent to run Meta. this man is literally becoming Tony Stark. it pulls data from every team inside the company so he can skip meetings, skip the chain of command, and make decisions faster than any human process allows. 78,000 employees have their own AI agents now too. one messages coworkers on your behalf. another acts as your AI chief of staff. their agents talk to each other in an internal network. humans optional. Meta also bought an entire social media platform built for AI agents to interact with each other. read that again. Zuck said he wants every person at Meta to have a personal AI agent. then every person outside Meta. the Jarvis era started.

sui

153,670 views • 6 months ago

AN ANTHROPIC LEAD ENGINEER ACCIDENTALLY LEAKED HIS PERSONAL OBSIDIAN. INSIDE - NOT CODE OR PROMPTS, BUT A DIAGRAM OF HIS OWN BRAIN, ORGANIZED AS A NEURAL NETWORK 8,893 nodes. 4,729 connections. A $10/month app opens Obsidian. 21 inputs, ReLU on every layer. The first hidden layer has 26 neurons, followed by 33, then 24, and so on all the way to the output. Thousands of connections flash in real time this isn’t a conceptual diagram from a blog, but a living brain that powers decision-making within the company. 9,000 documents, each with its own semantic space, all interconnected it earns about $2m a year for sorting Markdown files into the right folders. The company that builds the world’s best AI maintains its internal knowledge base in the same app that a freshman uses for class notes three years of discipline and a single open Obsidian tab you’re reading this on a device where, tonight, you can open that same Obsidian and start building your own vault
0:15

AN ANTHROPIC LEAD ENGINEER ACCIDENTALLY LEAKED HIS PERSONAL OBSIDIAN. INSIDE - NOT CODE OR PROMPTS, BUT A DIAGRAM OF HIS OWN BRAIN, ORGANIZED AS A NEURAL NETWORK 8,893 nodes. 4,729 connections. A $10/month app opens Obsidian. 21 inputs, ReLU on every layer. The first hidden layer has 26 neurons, followed by 33, then 24, and so on all the way to the output. Thousands of connections flash in real time this isn’t a conceptual diagram from a blog, but a living brain that powers decision-making within the company. 9,000 documents, each with its own semantic space, all interconnected it earns about $2m a year for sorting Markdown files into the right folders. The company that builds the world’s best AI maintains its internal knowledge base in the same app that a freshman uses for class notes three years of discipline and a single open Obsidian tab you’re reading this on a device where, tonight, you can open that same Obsidian and start building your own vault

chewa

359,674 views • 2 months ago