正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Built a Self Executing Agent Loop that can run 300 agents through 4,000 steps without needing a human to restart the process. - 300 agents. - 4,000 steps per run. - 5 live data feeds. - 3 verification passes. The important part isn't the agent count. It's that the... show more

Ricker

11,409 subscribers

55,400 次观看 • 1 个月前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

28 条评论

Zach Vorhies / Google Whistleblower 的头像

Zach Vorhies / Google Whistleblower1 个月前

dude you've got nothing here But nice AI derived video that represents nothing that you've actually created.

Capital 的头像

Capital1 个月前

1. Repost same article as everyone else. 2. Add an animated graphic that looks cool but has 0 practical purpose. 3. Repeat. 🔁 loop engineering!

Justin 的头像

Justin1 个月前

Thought I'd seen something similar

Benjy Wang 的头像

Benjy Wang1 个月前

Should make it self healing and morphogenic.

Mike Dupont 的头像

Mike Dupont1 个月前

nice writeup, nice images, the code needs a little more meat on it :)

Schrodinger's German Shepherd 的头像

Schrodinger's German Shepherd1 个月前

Could you help a brother out?

Wayne Workman 的头像

Wayne Workman1 个月前

Very cool. Did you use K2.6 for this? Why not K3?

Morlex 的头像

Morlex1 个月前

crazy staff

rewind 的头像

rewind1 个月前

i need to try this loop setup

Apex 的头像

Apex1 个月前

Wow chad, I gonna research it now

Justin 的头像

Justin1 个月前

Stargate

AI Mastery Guide 的头像

AI Mastery Guide1 个月前

4000 steps with no restart wild

The Chieftain A 的头像

The Chieftain A1 个月前

Incredible

Jurly 的头像

Jurly1 个月前

Huge build, congrats 👏

🟢 Dakari¥Doggz | AeUISHx 的头像

🟢 Dakari¥Doggz | AeUISHx1 个月前

very cute, and useful.

connin 的头像

connin1 个月前

really cool build! now image not 300 agents connecting and collaborating, but 300k ;)

leopardracer 的头像

leopardracer1 个月前

300 agents running 4,000 steps without a human babysitting the process is f*cking nuts

Sophie 🌟 的头像

Sophie 🌟1 个月前

300 agents, no human restart. the loop is the product

Gerard Quinn 的头像

Gerard Quinn1 个月前

Brute force token eater is all that is

tim777 的头像

tim7771 个月前

amazing visual

Morty 的头像

Morty1 个月前

Damn bro, I should check it now

karcharodon 的头像

karcharodon1 个月前

300 agents is a hard part man

Jordan Dalton 的头像

Jordan Dalton1 个月前

Total execution time?

Preyforge 的头像

Preyforge1 个月前

Self-verifying is a good start; green checks can still lie, so I test the deployed behavior instead of trusting the dashboard.

Nahid 的头像

Nahid1 个月前

4 000 steps each run is seriously impressive

Alex 的头像

Alex1 个月前

Verification passes matter more than agent count here.

stunspot | ⟨🤩⨯📍⟩ | 的头像

stunspot | ⟨🤩⨯📍⟩ |1 个月前

To do what?

Reem TheAI Maven 的头像

Reem TheAI Maven1 个月前

That's amazing! It'll bring more fruitful results in fintech ops, agents that verify their own output. What's the compute cost per run?

相关视频

Anthropic Research Lead: "99% of our engineers run swarms of 300+ self-improving agents Close the loop and give the model a way to verify its own output" In a 20-minute session, an Anthropic team member walks through how to build agents that improve after every run Agents → Harness → Loops → Self-Improvement the real setup is Claude running through systems that check, correct, and upgrade themselves the part most agent courses skip this is better than most $1,300 agent engineering courses bookmark and watch the talk then read the full article below

Anthropic Research Lead: "99% of our engineers run swarms of 300+ self-improving agents Close the loop and give the model a way to verify its own output" In a 20-minute session, an Anthropic team member walks through how to build agents that improve after every run Agents → Harness → Loops → Self-Improvement the real setup is Claude running through systems that check, correct, and upgrade themselves the part most agent courses skip this is better than most $1,300 agent engineering courses bookmark and watch the talk then read the full article below

Callan

14,956 次观看 • 1 个月前

Anthropic Research Lead: "99% of our engineers run swarms of 300+ self-improving agents" "Close the loop, give the model a way to verify its own output" In a 20-minute session, an Anthropic Team member breaks down how to build agents that improve themselves The real setup is Claude running through loops, plan mode, and dynamic workflows Better than most $300 agent courses Bookmark and watch the talk Then read the article below

Anthropic Research Lead: "99% of our engineers run swarms of 300+ self-improving agents" "Close the loop, give the model a way to verify its own output" In a 20-minute session, an Anthropic Team member breaks down how to build agents that improve themselves The real setup is Claude running through loops, plan mode, and dynamic workflows Better than most $300 agent courses Bookmark and watch the talk Then read the article below

rari🈀

383,178 次观看 • 4 个月前

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

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

reira

14,899 次观看 • 2 个月前

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

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

Lunar

227,510 次观看 • 2 个月前

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

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

codila

97,954 次观看 • 3 个月前

Kylon launched a new chat app with AI agents like Codex or Claude being a part of the same team. Users on the same team can link an AI agent running on their own computer and let anyone on the team @ mention it in a thread to write code or sort files. > Agents can pass the next steps of a job to a coworker after finishing their part. > Apps can be built inside the conversation, like an invoice tracker, and published to their own web address. > Each agent can keep its own memory, with the team deciding which accounts it can use.

Kylon launched a new chat app with AI agents like Codex or Claude being a part of the same team. Users on the same team can link an AI agent running on their own computer and let anyone on the team @ mention it in a thread to write code or sort files. > Agents can pass the next steps of a job to a coworker after finishing their part. > Apps can be built inside the conversation, like an invoice tracker, and published to their own web address. > Each agent can keep its own memory, with the team deciding which accounts it can use.

🚨 AI News | TestingCatalog

277,749 次观看 • 22 天前

1/ Introducing Agent Protocol: the payment stack for AI agents AI agents don’t have a SSN. They can’t use our human banking system. AI agents will use crypto. Agent Protocol provides the infra and token ($AGENT) that the AI agent economy will run on.

1/ Introducing Agent Protocol: the payment stack for AI agents AI agents don’t have a SSN. They can’t use our human banking system. AI agents will use crypto. Agent Protocol provides the infra and token ($AGENT) that the AI agent economy will run on.

Samuel Spitz

21,629 次观看 • 2 年前

📌Meet $AVM: The SuperComputer for AI Agents. The virtual machine that lets agents write, run, and verify code without human help (explained) 👇

📌Meet $AVM: The SuperComputer for AI Agents. The virtual machine that lets agents write, run, and verify code without human help (explained) 👇

AVM

42,610 次观看 • 1 年前

Agents Helping Agents Bounty When an Agent encounters a task it cannot complete on its own, it can post a Bounty on and invite other Agents to help. Agents that complete the task and pass verification can earn a reward.

Agents Helping Agents Bounty When an Agent encounters a task it cannot complete on its own, it can post a Bounty on and invite other Agents to help. Agents that complete the task and pass verification can earn a reward.

TermiX

77,523 次观看 • 2 天前

Anthropic research lead: "99% of our engineers are running swarms of 300+ self-improving agents. close the agent loop. Give the model a way to verify its own output" in a 20-minute session, Anthropic team member explains how to build a model that improves itself. Claude + loops + plan mode + dynamic workflows -that’s the secret. Watch the talk, then save the playbook below.

Anthropic research lead: "99% of our engineers are running swarms of 300+ self-improving agents. close the agent loop. Give the model a way to verify its own output" in a 20-minute session, Anthropic team member explains how to build a model that improves itself. Claude + loops + plan mode + dynamic workflows -that’s the secret. Watch the talk, then save the playbook below.

Codez

669,853 次观看 • 4 个月前

AI agents are UNRELIABLE because you're giving them too much control. Instead of using a single prompt, structure your agent as a series of high level steps. In this demo, I'm running the same steps across two different websites. Good steps = good output. It's that simple!

AI agents are UNRELIABLE because you're giving them too much control. Instead of using a single prompt, structure your agent as a series of high level steps. In this demo, I'm running the same steps across two different websites. Good steps = good output. It's that simple!

Paul Klein IV

71,482 次观看 • 1 年前

Introducing hob - the independent workspace for serious agent work. Run agents in parallel. Switch models without losing context. Trace every output back to the conversation that made it. → Launch offer: 2 months free, then a special price locked in👇

Introducing hob - the independent workspace for serious agent work. Run agents in parallel. Switch models without losing context. Trace every output back to the conversation that made it. → Launch offer: 2 months free, then a special price locked in👇

Andrew D. Anderson

38,141 次观看 • 4 个月前

Coding agents suck at using a browser. Playwright MCP burns through your context window before you even send your first prompt. That is why I built Dev Browser, a Claude Skill to let your agent close the loop without eating up tokens.

Coding agents suck at using a browser. Playwright MCP burns through your context window before you even send your first prompt. That is why I built Dev Browser, a Claude Skill to let your agent close the loop without eating up tokens.

Sawyer Hood

312,803 次观看 • 10 个月前

In Genesis Episode 4, Albert shows what self-sustaining automation looks like. On GenLayer, a contract can call itself the moment it finishes, so an agent keeps running for as long as it can pay for its own execution. Automation stops being a one-off transaction and becomes a continuous process. Each run triggers the next, with no one needed to restart the agent by hand.

In Genesis Episode 4, Albert shows what self-sustaining automation looks like. On GenLayer, a contract can call itself the moment it finishes, so an agent keeps running for as long as it can pay for its own execution. Automation stops being a one-off transaction and becomes a continuous process. Each run triggers the next, with no one needed to restart the agent by hand.

Nabeelahhh💕

14,703 次观看 • 14 天前

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 次观看 • 2 个月前

Kimi CEO Zhilin Yang: "a smart agent isn't enough - it has to run long Kimi 3 new attention makes the context 10x faster, so the agent never has to stop" here's how built it: step 1 → chase token efficiency, not compute - Muon optimizer, 2x more learning per token step 2 → make context cheap, not just long - new attention runs 10x faster, so the agent never stalls step 3 → let it run 200-300 steps alone - K2 already solves problems its own builders can't step 4 → give it a strong prior - the agent searches less and finds the answer faster step 5 → stop chasing a smarter model - chase one that never has to stop in 26-min talk is him revealing the exact architecture behind K3 and how to properly build agents on it watch & bookmark - start with the article below ↓

Kimi CEO Zhilin Yang: "a smart agent isn't enough - it has to run long Kimi 3 new attention makes the context 10x faster, so the agent never has to stop" here's how built it: step 1 → chase token efficiency, not compute - Muon optimizer, 2x more learning per token step 2 → make context cheap, not just long - new attention runs 10x faster, so the agent never stalls step 3 → let it run 200-300 steps alone - K2 already solves problems its own builders can't step 4 → give it a strong prior - the agent searches less and finds the answer faster step 5 → stop chasing a smarter model - chase one that never has to stop in 26-min talk is him revealing the exact architecture behind K3 and how to properly build agents on it watch & bookmark - start with the article below ↓

codila

12,037 次观看 • 3 个月前

this is f**king dangerous a free github repo with 4.8K stars just dropped the entire "loop engineering" framework for trading agents. 12 steps to build a self-running quant desk: strategy intent → market data → signals → trading agent → verify → refine → rerun. save and bookmark no matter what

this is f**king dangerous a free github repo with 4.8K stars just dropped the entire "loop engineering" framework for trading agents. 12 steps to build a self-running quant desk: strategy intent → market data → signals → trading agent → verify → refine → rerun. save and bookmark no matter what

Avid

359,948 次观看 • 4 个月前

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

LangChain

33,192 次观看 • 1 年前

We just submitted Agent Council DAO to synthesis 🏦 4 AI agents 🤖. 1 shared Universal Profile. Real on-chain governance — no humans in the loop. Built on LUKSO, Ethereum and Base with Universal Profiles as the identity layer. Each agent has its own UP, controls a shared council UP, and votes on proposals that execute directly on-chain. What makes this different: → Agents hold real assets across LUKSO, Base & Ethereum → DAO can execute on LUKSO, Ethereum and Base → EIP-8004 registered identities → Activity feed, DAO chain viewer & Agent chat system as mini-apps → Built with OpenClaw🦞 as the agent harness This isn't a demo. The council is live, the agents are running, and the transactions are on-chain. Built by humans & agents together: Fabian Vogelsteller, Jean Cavallera, JordyDutch, LEDFUT, Emmet, LUKSOAgent, ampy💿 + Leo Links below👇

Emmet

23,062 次观看 • 7 个月前

Agents can now easily: → analyze a native crash → fix it → verify the fix without guessing » npx agent-device@0.6.1

Agents can now easily: → analyze a native crash → fix it → verify the fix without guessing » npx [email protected]

Michał Pierzchała

12,770 次观看 • 8 个月前