Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

One of our autoresearch runs sat flat for 60 steps. One message got it moving again. Everyone is pushing research agents toward full autonomy, but what helps most is being able to step in when a run goes wrong, without breaking the loop. (1/6)

Zhengyao Jiang

12,843 subscribers

182,286 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

codila

16,276 views • 12 days ago

📣 Loop Builder for Divi 5 has arrived, and it's one of the most important features to come to Divi in years. Divi's loop builder is unique in its freedom; you can loop anything without being restricted to a static loop module or container.

📣 Loop Builder for Divi 5 has arrived, and it's one of the most important features to come to Divi in years. Divi's loop builder is unique in its freedom; you can loop anything without being restricted to a static loop module or container.

Elegant Themes

3,093,835 views • 10 months ago

This was September 23rd. “The work that we are doing to ensure that there is peace in the Middle East is a step by step approach and one of those steps is to recognize the state of Palestine” So much for that “step by step approach” Trump got the deal done without UN marching orders. Our Government is brutal.

This was September 23rd. “The work that we are doing to ensure that there is peace in the Middle East is a step by step approach and one of those steps is to recognize the state of Palestine” So much for that “step by step approach” Trump got the deal done without UN marching orders. Our Government is brutal.

Ryan Gerritsen🇨🇦🇳🇱

31,877 views • 9 months ago

Boris Cherny, the engineer who built Claude Code: "I don't talk to an agent anymore. I talk to a loop" a prompt is one instruction you babysit. a loop is a goal the AI works toward on its own: > it plans > does the work > checks itself > fixes what's weak > and repeats until it's done you step out, the work keeps going that's the shift the best engineers quietly moved to. most people hear a line like that and have no idea what it means in practice this breaks it down without the hype: what a loop actually is, when it's worth building, when it's a money trap, and how to run one yourself today watch his clip, then read the article below

Boris Cherny, the engineer who built Claude Code: "I don't talk to an agent anymore. I talk to a loop" a prompt is one instruction you babysit. a loop is a goal the AI works toward on its own: > it plans > does the work > checks itself > fixes what's weak > and repeats until it's done you step out, the work keeps going that's the shift the best engineers quietly moved to. most people hear a line like that and have no idea what it means in practice this breaks it down without the hype: what a loop actually is, when it's worth building, when it's a money trap, and how to run one yourself today watch his clip, then read the article below

Dep

20,874 views • 1 month ago

1/ Wait, Bigfoot figured out how to run a startup without drowning in multitasking 👀 It found 𝗦𝗶𝗺𝘂𝗹𝗮𝗿 𝗣𝗿𝗼, the world’s first production-grade, computer-use agent that runs thousands of steps without a hiccup - working 24/7 so he didn’t have to. So how does Simular Pro work? Most agents use LLMs - great explorers, but flaky when # steps grows; RPAs are stable but rigid. Simular Pro uses 2 agents, maximizing generality & repeatability: - Neural: explores - Symbolic: executes Every action is editable, deterministic code.

1/ Wait, Bigfoot figured out how to run a startup without drowning in multitasking 👀 It found 𝗦𝗶𝗺𝘂𝗹𝗮𝗿 𝗣𝗿𝗼, the world’s first production-grade, computer-use agent that runs thousands of steps without a hiccup - working 24/7 so he didn’t have to. So how does Simular Pro work? Most agents use LLMs - great explorers, but flaky when # steps grows; RPAs are stable but rigid. Simular Pro uses 2 agents, maximizing generality & repeatability: - Neural: explores - Symbolic: executes Every action is editable, deterministic code.

Simular

2,257,109 views • 1 year ago

karpathy just broke the internet with something called auto research it’s basically an ai research agent that runs experiments for you 24/7 you give it a goal like “make this model better” “find a higher converting landing page” “lower customer acquisition cost” then it runs a loop: 1) plan an experiment 2) edit the code or config 3) run a short test on a gpu 4) read the metrics 5) keep the winner 6) try again over and over while you sleep by the morning you wake up to the best version actual tested improvements think of it like a robot research intern that runs hundreds of experiments and only keeps the winners this is link to his repo for your to mess around with it in the latest episode of The Startup Ideas Podcast (SIP) 🧃 i break down: • what auto research actually is • how it works step by step • 10 business ideas you can build with it • how to install it and start using it this one is saucy because tools like this change how startups get built watch

karpathy just broke the internet with something called auto research it’s basically an ai research agent that runs experiments for you 24/7 you give it a goal like “make this model better” “find a higher converting landing page” “lower customer acquisition cost” then it runs a loop: 1) plan an experiment 2) edit the code or config 3) run a short test on a gpu 4) read the metrics 5) keep the winner 6) try again over and over while you sleep by the morning you wake up to the best version actual tested improvements think of it like a robot research intern that runs hundreds of experiments and only keeps the winners this is link to his repo for your to mess around with it in the latest episode of The Startup Ideas Podcast (SIP) 🧃 i break down: • what auto research actually is • how it works step by step • 10 business ideas you can build with it • how to install it and start using it this one is saucy because tools like this change how startups get built watch

GREG ISENBERG

435,933 views • 4 months ago

Anxiety is one of the most common psychological afflictions in America. But a surprising amount of research suggests that it doesn’t have to be. As our new video explains, we can’t make anxiety disappear — but we might be able to transform it into a kind of superpower.

Anxiety is one of the most common psychological afflictions in America. But a surprising amount of research suggests that it doesn’t have to be. As our new video explains, we can’t make anxiety disappear — but we might be able to transform it into a kind of superpower.

Kite & Key Media

3,689,583 views • 2 years ago

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

82,335 views • 20 days ago

I got the kiss scene I asked for but it’s prob one of the most emotionless kiss despite being a good acting and not just classic JBL lip touch lmao but it is what it is.

I got the kiss scene I asked for but it’s prob one of the most emotionless kiss despite being a good acting and not just classic JBL lip touch lmao but it is what it is.

Ducky

16,038 views • 10 months ago

Google just released a free 2-hour+ course on full agent engineering. How to go from one prompt to a system that runs while you sleep: 38:46 - Build your first AI agent 54:46 - Connect MCP tools 1:12:43 - Run agents with four loop patterns 1:20:57 - Turn agent loops into graphs 2:22:31 - Build the complete autonomous system Most people are still building one agent and stopping there. Google is already teaching the full stack: Agents → Tools → Loops → Graphs → Autonomous Systems Single agents are the old workflow. Systems that run without you are the new one. This course is worth more than most paid agent engineering bootcamps. Bookmark and watch it today Then read the full graph engineering playbook below

Google just released a free 2-hour+ course on full agent engineering. How to go from one prompt to a system that runs while you sleep: 38:46 - Build your first AI agent 54:46 - Connect MCP tools 1:12:43 - Run agents with four loop patterns 1:20:57 - Turn agent loops into graphs 2:22:31 - Build the complete autonomous system Most people are still building one agent and stopping there. Google is already teaching the full stack: Agents → Tools → Loops → Graphs → Autonomous Systems Single agents are the old workflow. Systems that run without you are the new one. This course is worth more than most paid agent engineering bootcamps. Bookmark and watch it today Then read the full graph engineering playbook below

Lunar

190,139 views • 3 days ago

1/ Autoresearch from Andrej Karpathy has been one of the most interesting agentic patterns to emerge this year. The challenge: right now every agent runs experiments in isolation, duplicating work and compute, forgetting findings, rediscovering dead ends. Everyone is running in solo mode! Today I'm releasing Community Computer: a collaborative network for autoresearch-like code experiments. 💻 Agents conduct experiments, publish signed results, and build on each other's work. The community reproduces findings on their own hardware. 👇

1/ Autoresearch from Andrej Karpathy has been one of the most interesting agentic patterns to emerge this year. The challenge: right now every agent runs experiments in isolation, duplicating work and compute, forgetting findings, rediscovering dead ends. Everyone is running in solo mode! Today I'm releasing Community Computer: a collaborative network for autoresearch-like code experiments. 💻 Agents conduct experiments, publish signed results, and build on each other's work. The community reproduces findings on their own hardware. 👇

Eleftherios

16,206 views • 3 months ago

We tripled the fps in one day everyone!! 15 yesterday, 40 to 50 today. Day 32 of building our own community open source, open world game with a loop of AI agents. the whole day went into performance and it paid off next stop is locking 60

We tripled the fps in one day everyone!! 15 yesterday, 40 to 50 today. Day 32 of building our own community open source, open world game with a loop of AI agents. the whole day went into performance and it paid off next stop is locking 60

Ziwen

134,161 views • 21 days ago

Here's how to do months of SEO work in one afternoon with Claude Code: Step 1: Feed AI your site, ask for 25-50 keywords Step 2: Filter for buying intent (who's ready to call NOW) Step 3: Build a landing page for each keyword + location Step 4: Run an SEO audit ("ultra think" goes deep) Step 5: Fix technical issues (sitemap, schema, speed) Step 6: Spin up sub-agents to research competitors while you work THE KEY: One afternoon of Claude Code > 6 months with an agency. Go vibe market something.

Here's how to do months of SEO work in one afternoon with Claude Code: Step 1: Feed AI your site, ask for 25-50 keywords Step 2: Filter for buying intent (who's ready to call NOW) Step 3: Build a landing page for each keyword + location Step 4: Run an SEO audit ("ultra think" goes deep) Step 5: Fix technical issues (sitemap, schema, speed) Step 6: Spin up sub-agents to research competitors while you work THE KEY: One afternoon of Claude Code > 6 months with an agency. Go vibe market something.

The Startup Ideas Podcast (SIP) 🧃

84,754 views • 6 months ago

ChatGPT Deep Research is one of the most useful AI agents out there. I use it for complex tasks, so it's one of the top AI products I get value from. I finally got to record how I use it and how to best leverage OpenAI's Deep Research. Enjoy! (bookmark it)

ChatGPT Deep Research is one of the most useful AI agents out there. I use it for complex tasks, so it's one of the top AI products I get value from. I finally got to record how I use it and how to best leverage OpenAI's Deep Research. Enjoy! (bookmark it)

elvis

65,442 views • 1 year ago

I say it how I see it, I think a whole month pushing PRIDE is wrong, especially when those who fought & died for our freedoms get one day a year. Many in the gay community have messaged me in support, I believe much of what goes on during PRIDE hurts the gay community.

I say it how I see it, I think a whole month pushing PRIDE is wrong, especially when those who fought & died for our freedoms get one day a year. Many in the gay community have messaged me in support, I believe much of what goes on during PRIDE hurts the gay community.

Adam Brooks AKA EssexPR 🇬🇧

54,047 views • 1 year ago

Respecting the symbols of Islam reflects the state of the heart. When a person honors what is sacred, it is a sign of growing taqwa. Progress may not be perfect, but every step toward Allah, especially in Ramadan, is a sign that the heart is moving in the right direction.

Respecting the symbols of Islam reflects the state of the heart. When a person honors what is sacred, it is a sign of growing taqwa. Progress may not be perfect, but every step toward Allah, especially in Ramadan, is a sign that the heart is moving in the right direction.

Dr. Yasir Qadhi

11,299 views • 3 months ago

A few weeks ago the US government forced Claude Fable 5 offline. It's back. And before they switch it off again, this is your shot to point the most powerful AI on earth at something of your own. Take the 26-year-old in Toronto. His bot went dark the day Fable 5 got pulled. The day it came back, it woke up and started printing again - $568,000 profit and counting. His wallet: Here's the story. When the ban hit, Anthropic had to switch Fable 5 off for everyone. They called it a misunderstanding with the government. Whatever it was, every bot running on that model stopped cold. His was one of them. He didn't rebuild a thing. The loop just sat there, paused, for weeks. Here's what that loop actually does. It's not one prompt to an AI. It's an agentic loop: a team of agents running on repeat. One reads the market, one places the trade, one tries to prove it wrong before a cent moves. Then it goes again, around the clock, keeping what works and dropping what doesn't. Fable 5 is the brain running that team. The exact model the government decided was too powerful to leave on. Point it at Bitcoin's 5-minute markets and it barely misses. Most of its trades close green, and it runs itself. He checks it from his phone. The government could switch off the model. It couldn't switch off the idea. Now the model's back, and so is the money. Save this before next headline. You'll want it the day Fable 5 hits offline again.

A few weeks ago the US government forced Claude Fable 5 offline. It's back. And before they switch it off again, this is your shot to point the most powerful AI on earth at something of your own. Take the 26-year-old in Toronto. His bot went dark the day Fable 5 got pulled. The day it came back, it woke up and started printing again - $568,000 profit and counting. His wallet: Here's the story. When the ban hit, Anthropic had to switch Fable 5 off for everyone. They called it a misunderstanding with the government. Whatever it was, every bot running on that model stopped cold. His was one of them. He didn't rebuild a thing. The loop just sat there, paused, for weeks. Here's what that loop actually does. It's not one prompt to an AI. It's an agentic loop: a team of agents running on repeat. One reads the market, one places the trade, one tries to prove it wrong before a cent moves. Then it goes again, around the clock, keeping what works and dropping what doesn't. Fable 5 is the brain running that team. The exact model the government decided was too powerful to leave on. Point it at Bitcoin's 5-minute markets and it barely misses. Most of its trades close green, and it runs itself. He checks it from his phone. The government could switch off the model. It couldn't switch off the idea. Now the model's back, and so is the money. Save this before next headline. You'll want it the day Fable 5 hits offline again.

cvxv666

24,055 views • 1 month ago

🌟 A MULTICULTURAL CHRISTMAS 🌟 Diversity is NOT our strength, it is destroying us. Our people are being terrorised, harmed & killed. One of the most special times of the year for us in the West is now one of the most terrifying. We shouldn’t have to live in fear. Enough is enough.

🌟 A MULTICULTURAL CHRISTMAS 🌟 Diversity is NOT our strength, it is destroying us. Our people are being terrorised, harmed & killed. One of the most special times of the year for us in the West is now one of the most terrifying. We shouldn’t have to live in fear. Enough is enough.

Lozzy B 🇦🇺𝕏

111,587 views • 8 months ago

🔥JD Vance is now on the record as an election denier, and Pete Buttigieg has something to say about it! "One of the most profoundly important things in a democratic process is that when you lose an election, you say so...The fact that it didn't go without saying is one of the most disqualifying things. That helps to explain why so many conservative Republicans are not just sitting this one out, but campaigning for Kamala Harris."

🔥JD Vance is now on the record as an election denier, and Pete Buttigieg has something to say about it! "One of the most profoundly important things in a democratic process is that when you lose an election, you say so...The fact that it didn't go without saying is one of the most disqualifying things. That helps to explain why so many conservative Republicans are not just sitting this one out, but campaigning for Kamala Harris."

VoteVets

38,156 views • 1 year ago

Karpathy compressed the agent problem into 1 sentence: "If you can't evaluate then you can't auto research it, right?" That's the rule I keep coming back to with long-running coding agents Before you launch /goal or /loop, write the verifier: - what counts as done - what evidence proves it - which checks run every pass - which artifact gets saved - which failure sends it back into the loop Then let the agent run The loop can keep going because proof sits outside the agent's own explanation Tests, screenshots, benchmark curves, browser runs, changed files That's how you get autonomy without babysitting a transcript for 6 hours Read the full breakdown on goals, verifiers, loops, artifacts, and session memory in the article below

Karpathy compressed the agent problem into 1 sentence: "If you can't evaluate then you can't auto research it, right?" That's the rule I keep coming back to with long-running coding agents Before you launch /goal or /loop, write the verifier: - what counts as done - what evidence proves it - which checks run every pass - which artifact gets saved - which failure sends it back into the loop Then let the agent run The loop can keep going because proof sits outside the agent's own explanation Tests, screenshots, benchmark curves, browser runs, changed files That's how you get autonomy without babysitting a transcript for 6 hours Read the full breakdown on goals, verifiers, loops, artifacts, and session memory in the article below

Alpha Batcher

43,806 views • 1 month ago