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。

Loop Engineering is getting hype now. But not many talks about how to actually do it So I open-sourced the template my team uses to build agent loops: - a shared artifact / knowledge layer - logging, verification - and a codebase harness so work compounds across runs Plus... show more

Jason Zhou

32,065 subscribers

387,476 次观看 • 27 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I gave my coding agent a map across 3 of my repos: - Reduce ~50% token - a grep hook so every grep call has much richer info - trace any function's call chain + blast radius Really can feel my agent is getting A LOT smarter; I added to my codebase setup skill + 8-min deep dive: Copy it. Adapt it to your codebase.

I gave my coding agent a map across 3 of my repos: - Reduce ~50% token - a grep hook so every grep call has much richer info - trace any function's call chain + blast radius Really can feel my agent is getting A LOT smarter; I added to my codebase setup skill + 8-min deep dive: Copy it. Adapt it to your codebase.

Jason Zhou

81,271 次观看 • 19 天前

I put an entire codebase in a text file and gave it to Gemini 1.5 Pro. I gave it a task that required updating ~10 files across the entire codebase - so decently complex. It got about 80% of the work done for me on a 1st attempt. Watch to see in-depth on how it performed.

I put an entire codebase in a text file and gave it to Gemini 1.5 Pro. I gave it a task that required updating ~10 files across the entire codebase - so decently complex. It got about 80% of the work done for me on a 1st attempt. Watch to see in-depth on how it performed.

Mckay Wrigley

85,698 次观看 • 2 年前

I created a 2D template for Unreal Engine 5 and decided to make it open source and free for everybody! Please share the template and fork it to make your own versions of it. #indiedev #gamedev #unrealengine #ue5

I created a 2D template for Unreal Engine 5 and decided to make it open source and free for everybody! Please share the template and fork it to make your own versions of it. #indiedev #gamedev #unrealengine #ue5

Cobra Code

140,563 次观看 • 2 年前

Head of Engineering Shopify: "AI writes the code, AI reviews the code. Your job is just to write the loops around it." 26 minutes on how AI changed the way 3,000 engineers work inside a single company. Ignoring it while everyone else uses AI to do more is the fastest way to fall behind. Watch it, then read the step by step guide on loops below.

Head of Engineering Shopify: "AI writes the code, AI reviews the code. Your job is just to write the loops around it." 26 minutes on how AI changed the way 3,000 engineers work inside a single company. Ignoring it while everyone else uses AI to do more is the fastest way to fall behind. Watch it, then read the step by step guide on loops below.

Anatoli Kopadze

710,184 次观看 • 24 天前

an OpenAI engineer just showed how he gets agents to do his whole job: code, debug and more, using loops 29 minutes from the engineer who coined "harness engineering" he writes the rules, agents write the code, a reviewer agent loops until it's right the winners won't have the smartest model, they'll have the best loop around it watch it, then read the full guide on loops below

an OpenAI engineer just showed how he gets agents to do his whole job: code, debug and more, using loops 29 minutes from the engineer who coined "harness engineering" he writes the rules, agents write the code, a reviewer agent loops until it's right the winners won't have the smartest model, they'll have the best loop around it watch it, then read the full guide on loops below

Anatoli Kopadze

175,745 次观看 • 27 天前

imagine how powerful your AI chatbot would be if you could hook it up to your own knowledge base? I just made a full walkthrough on how to build your own AI chatbot powered by your custom knowledge base inside, I cover: – how to gather and clean your docs + conversations – chunking + embeddings (so your AI actually remembers details) – setting up a vector database – connecting RAG so the bot pulls the right info when asked – deployment: getting it live for real users reply “RAG” and I’ll DM you the walkthrough + code (must be following)

imagine how powerful your AI chatbot would be if you could hook it up to your own knowledge base? I just made a full walkthrough on how to build your own AI chatbot powered by your custom knowledge base inside, I cover: – how to gather and clean your docs + conversations – chunking + embeddings (so your AI actually remembers details) – setting up a vector database – connecting RAG so the bot pulls the right info when asked – deployment: getting it live for real users reply “RAG” and I’ll DM you the walkthrough + code (must be following)

Tyler

16,635 次观看 • 10 个月前

x402 is finally catching fire, but how do you actually build with it? In this video you'll learn how to build custom x402 agents in just 5 minutes. 🔥 The app is Open Source and gets you started with both a client and a merchant agent, everything you need to build your own agents. I show you how to extend it to sell EBooks for 1USDC.

x402 is finally catching fire, but how do you actually build with it? In this video you'll learn how to build custom x402 agents in just 5 minutes. 🔥 The app is Open Source and gets you started with both a client and a merchant agent, everything you need to build your own agents. I show you how to extend it to sell EBooks for 1USDC.

nader dabit

173,493 次观看 • 8 个月前

OpenClaw just got a plugin nobody is talking about. And it can replace a whole operations team. It is called Paperclip. It lets you build a full AI company on your own computer. You get an AI CEO. You get a marketing team. You get a tech team. They have real memory so they never forget a task. They wake up every day and do the work for you. You do not have to manage them or pay them a salary. Your data stays safe because it runs on your hardware. Here is how to start today. Go to GitHub and download OpenClaw. Install the Paperclip dashboard inside it. Pick one task and hire your first AI worker.

OpenClaw just got a plugin nobody is talking about. And it can replace a whole operations team. It is called Paperclip. It lets you build a full AI company on your own computer. You get an AI CEO. You get a marketing team. You get a tech team. They have real memory so they never forget a task. They wake up every day and do the work for you. You do not have to manage them or pay them a salary. Your data stays safe because it runs on your hardware. Here is how to start today. Go to GitHub and download OpenClaw. Install the Paperclip dashboard inside it. Pick one task and hire your first AI worker.

Julian Goldie SEO

33,889 次观看 • 4 个月前

GPT Engineer github: Specify what you want it to build, the AI asks for clarification, and then builds it. GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.

GPT Engineer github: Specify what you want it to build, the AI asks for clarification, and then builds it. GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.

AK

349,147 次观看 • 3 年前

Seeing so many people talking about this current viral wave This guy specifically brings up how useless it is to go to the doctor, how weird it is that years ago we tried to mitigate spread, and how "something's going on but nobody talks about it anymore bc it's not on TV"

Seeing so many people talking about this current viral wave This guy specifically brings up how useless it is to go to the doctor, how weird it is that years ago we tried to mitigate spread, and how "something's going on but nobody talks about it anymore bc it's not on TV"

chip! ☽☾🍉

4,823,560 次观看 • 6 个月前

HOW TO USE AI LOOPS TO RUN YOUR BUSINESS 24/7 A lot has been written about loop engineering for building products. Almost nothing about using loops to run the business itself. That's the bigger idea. A loop is when you give an agent a goal, a way to check its own work, and permission to keep trying until it hits that goal. Build. Verify. Repeat. Stop when the condition is met. Here's what it looks like in practice: 1/SEO loop You're position 30 for a term you want. The loop runs once a month, makes changes, checks where you rank, and keeps pushing until you're on page one. This is running in production right now on Inbox Zero. 2/Ads loop You're spending $100 a day and losing money. The loop tests creative, checks profitability, kills what fails, and keeps going until the account is in the black. 3/Eval loop Your AI feature is only 88% accurate. The loop keeps adjusting the prompt and swapping the model until it passes 90%. 4/LLM visibility loop People search in ChatGPT now, not just Google. Same loop, new scoreboard. Are we the answer or not? The whole thing hinges on one thing: a metric that comes back black and white. Where do I rank? Did it hit profitability? Did the evals pass? Give an agent that scoreboard and it runs for months. Loops used to run for 30 minutes. These run for a year. Take a step, sleep, wake up next month, take another one. You're basically hiring an agency that never sleeps, gets paid in tokens instead of invoices, and undoes its own mistakes when the number goes down. Full episode on The Startup Ideas Podcast (SIP) 🧃 watch

HOW TO USE AI LOOPS TO RUN YOUR BUSINESS 24/7 A lot has been written about loop engineering for building products. Almost nothing about using loops to run the business itself. That's the bigger idea. A loop is when you give an agent a goal, a way to check its own work, and permission to keep trying until it hits that goal. Build. Verify. Repeat. Stop when the condition is met. Here's what it looks like in practice: 1/SEO loop You're position 30 for a term you want. The loop runs once a month, makes changes, checks where you rank, and keeps pushing until you're on page one. This is running in production right now on Inbox Zero. 2/Ads loop You're spending $100 a day and losing money. The loop tests creative, checks profitability, kills what fails, and keeps going until the account is in the black. 3/Eval loop Your AI feature is only 88% accurate. The loop keeps adjusting the prompt and swapping the model until it passes 90%. 4/LLM visibility loop People search in ChatGPT now, not just Google. Same loop, new scoreboard. Are we the answer or not? The whole thing hinges on one thing: a metric that comes back black and white. Where do I rank? Did it hit profitability? Did the evals pass? Give an agent that scoreboard and it runs for months. Loops used to run for 30 minutes. These run for a year. Take a step, sleep, wake up next month, take another one. You're basically hiring an agency that never sleeps, gets paid in tokens instead of invoices, and undoes its own mistakes when the number goes down. Full episode on The Startup Ideas Podcast (SIP) 🧃 watch

GREG ISENBERG

80,088 次观看 • 6 天前

THIS 11-PAGE CLAUDE LOOP ENGINEERING PLAYBOOK IS THE CHEAT CODE FOR SENIOR DEV PROMOTIONS typing prompts line by line won't get you hired. you need to know how to design self-prompting loops: > Discovery: agent finds its own work from logs, failing tests, and commits > Handoff: tasks execute in isolated git worktrees to prevent parallel collisions > Verification: a second reviewer agent audits the builder's code to catch blind spots > Persistence and Scheduling: code writes to disk and loops run 24/7 on a timer the shift is simple: stop prompting the agent, build the system that prompts it read the full setup blueprint 👇

THIS 11-PAGE CLAUDE LOOP ENGINEERING PLAYBOOK IS THE CHEAT CODE FOR SENIOR DEV PROMOTIONS typing prompts line by line won't get you hired. you need to know how to design self-prompting loops: > Discovery: agent finds its own work from logs, failing tests, and commits > Handoff: tasks execute in isolated git worktrees to prevent parallel collisions > Verification: a second reviewer agent audits the builder's code to catch blind spots > Persistence and Scheduling: code writes to disk and loops run 24/7 on a timer the shift is simple: stop prompting the agent, build the system that prompts it read the full setup blueprint 👇

Mr. Buzzoni

44,111 次观看 • 24 天前

My friend at Anthropic makes $1.4M a year. No MIT. No Stanford. No PhD. I asked how their team actually ships autonomous agents. He sent me an article most AI engineers missed. It unpacks Anthropic's entire loop-engineering playbook: the 3-agent harness, all the team's internal essays, and how to copy it. Bookmark it. Then read this setup ↓

My friend at Anthropic makes $1.4M a year. No MIT. No Stanford. No PhD. I asked how their team actually ships autonomous agents. He sent me an article most AI engineers missed. It unpacks Anthropic's entire loop-engineering playbook: the 3-agent harness, all the team's internal essays, and how to copy it. Bookmark it. Then read this setup ↓

Archive

54,058 次观看 • 6 天前

🖼️ Making the perfect Lobby Background for your Fortnite Creators game could be a bit tricky So here is a thread on how to craft the perfect one inside UEFN, including how to preview it and export it with my Photoshop template Let's go! 👇🧵

🖼️ Making the perfect Lobby Background for your Fortnite Creators game could be a bit tricky So here is a thread on how to craft the perfect one inside UEFN, including how to preview it and export it with my Photoshop template Let's go! 👇🧵

Javi Romero

24,064 次观看 • 1 年前

My Framer template was rejected ❌ This isn't what I was hoping to post but I always try to share both the ups and downs. I put the most effort ever into this template but ultimately it was rejected for originality. The agency niche is completely new to me and although I learnt a lot during the process, I obviously didn't do a good enough job making it unique enough so I have a lot to learn there still. I'm feeling a bit lost on what to do with this template as I really like it but I'd have to drastically change it (colours, fonts, content, etc...) to get it live on the marketplace. Maybe I'll just make it live on my own store incase anyone is interested in it still? As always massive respect to the Framer review team for upholding such high marketplace standards. Not going to let this keep me down for too long, I'm moving straight onto my next template and going for something more simple and similar to what has worked for me before (think a Refit 2.0) 💪🏻

My Framer template was rejected ❌ This isn't what I was hoping to post but I always try to share both the ups and downs. I put the most effort ever into this template but ultimately it was rejected for originality. The agency niche is completely new to me and although I learnt a lot during the process, I obviously didn't do a good enough job making it unique enough so I have a lot to learn there still. I'm feeling a bit lost on what to do with this template as I really like it but I'd have to drastically change it (colours, fonts, content, etc...) to get it live on the marketplace. Maybe I'll just make it live on my own store incase anyone is interested in it still? As always massive respect to the Framer review team for upholding such high marketplace standards. Not going to let this keep me down for too long, I'm moving straight onto my next template and going for something more simple and similar to what has worked for me before (think a Refit 2.0) 💪🏻

JJ Gerrish

13,694 次观看 • 7 个月前

Boris Cherny (Claude Code creator): "I don't prompt Claude anymore... my job is to write loops." In his latest interview, he breaks down the setup step by step. He runs /loops + a dynamic workflow + a couple hundred agents that read his GitHub, Slack, and Twitter and decide what to build next. His only job now is writing the loops that orchestrate them. That's a multi-agent workflow. I broke down how to build your own below ↓

Boris Cherny (Claude Code creator): "I don't prompt Claude anymore... my job is to write loops." In his latest interview, he breaks down the setup step by step. He runs /loops + a dynamic workflow + a couple hundred agents that read his GitHub, Slack, and Twitter and decide what to build next. His only job now is writing the loops that orchestrate them. That's a multi-agent workflow. I broke down how to build your own below ↓

Avid

26,751 次观看 • 1 个月前

everybody talks about building AI automations but no one talks about how to evaluate if they’re actually working — especially at scale that’s why I put together a practical walkthrough on how to track AI performance in real-time using live dashboards inside, I cover: - context relevance: is the AI actually using what we give it? - gap detection: where your knowledge base is falling short - tracking: how to log and monitor outputs across any AI system - hallucination checks: flagging when the model starts making stuff up reply “track” and I’ll send it to you (must be following so I can DM)

everybody talks about building AI automations but no one talks about how to evaluate if they’re actually working — especially at scale that’s why I put together a practical walkthrough on how to track AI performance in real-time using live dashboards inside, I cover: - context relevance: is the AI actually using what we give it? - gap detection: where your knowledge base is falling short - tracking: how to log and monitor outputs across any AI system - hallucination checks: flagging when the model starts making stuff up reply “track” and I’ll send it to you (must be following so I can DM)

Tyler

21,624 次观看 • 1 年前

Anthropic just released 5 Claude workshops on the new skill every AI builder needs: Loop Engineering: 00:00 - Stop babysitting your agents 37:07 - Build a proactive Claude Code loop 1:11:23 - Build a production-ready Managed Agent 1:38:46 - Teach agents to learn from your team 2:07:15 - Hill-climb your agent with eval loops It is a 2 hour and 25 minute blueprint for Loop Engineering: proactive workflows, managed agents, team feedback, evals, and self-improvement. Watch it today, and read the article below to improve your skills with Fable 5.

Anthropic just released 5 Claude workshops on the new skill every AI builder needs: Loop Engineering: 00:00 - Stop babysitting your agents 37:07 - Build a proactive Claude Code loop 1:11:23 - Build a production-ready Managed Agent 1:38:46 - Teach agents to learn from your team 2:07:15 - Hill-climb your agent with eval loops It is a 2 hour and 25 minute blueprint for Loop Engineering: proactive workflows, managed agents, team feedback, evals, and self-improvement. Watch it today, and read the article below to improve your skills with Fable 5.

Alex

46,088 次观看 • 11 天前

Your agent already knew how to write. Now it knows how to show up. HeyGen Skills Describe your avatar or paste a photo. Your agent builds it, saves it for every future video, and engineers the prompt so your message actually lands. check the link below to get started 👇

HeyGen

432,545 次观看 • 3 个月前

Hermes agent is insane I gave Hermes access to Browser Use so it has access to my social media accounts. It retains context about my codebase, tone, and workflows. Now i just ask it to post on X for me...

Hermes agent is insane I gave Hermes access to Browser Use so it has access to my social media accounts. It retains context about my codebase, tone, and workflows. Now i just ask it to post on X for me...

shawn

121,027 次观看 • 4 个月前