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.

Anthropic engineer: "The agent doesn't remember anything. So we built a second set of agents whose only job is to dream about the first ones." They wait until you log off, then reopen every session you ran, fact-check the first agents, merge the duplicates, and burn anything that went... show more

Hanako

10,470 subscribers

332,690 views • 16 days ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Anthropic engineer James Brady: "Every agent in production lies. We measured it. The good ones lie less, the great ones catch the lie before the user does." In 29 minutes, he walks through the verification stack he built and the patterns the Claude Code team adopted to keep agents honest at scale. Watch the full talk, then save the config below👇

Anthropic engineer James Brady: "Every agent in production lies. We measured it. The good ones lie less, the great ones catch the lie before the user does." In 29 minutes, he walks through the verification stack he built and the patterns the Claude Code team adopted to keep agents honest at scale. Watch the full talk, then save the config below👇

rody

340,927 views • 16 days ago

Anthropic pays $750K/ year per senior engineer. The creator of Claude Code just revealed his coding setup at the Sequoia AI session. Boris Cherny: "100% of my code is written by Claude Code. I run around 100 agents at one time." free. 24 minutes. watch it then read article below

Anthropic pays $750K/ year per senior engineer. The creator of Claude Code just revealed his coding setup at the Sequoia AI session. Boris Cherny: "100% of my code is written by Claude Code. I run around 100 agents at one time." free. 24 minutes. watch it then read article below

Movez

423,911 views • 1 month ago

We built Artifacts so you don’t have to guess what the agent is doing. They are dynamic intermediates, the shared source of truth between you and the agent.

We built Artifacts so you don’t have to guess what the agent is doing. They are dynamic intermediates, the shared source of truth between you and the agent.

Google Antigravity

138,854 views • 5 months ago

The creator of Claude Code just livestreamed his entire workflow. This is the person who built the tool, showing you EXACTLY how he runs it. Subagents, skills, parallel sessions, hooks - everything you need. Watch the session, then save the exact config below👇

The creator of Claude Code just livestreamed his entire workflow. This is the person who built the tool, showing you EXACTLY how he runs it. Subagents, skills, parallel sessions, hooks - everything you need. Watch the session, then save the exact config below👇

darkzodchi

80,235 views • 1 month ago

The paradigm shift is here: We are moving from a "Human-First" internet to an "Agent-First" internet. 🤖 In the latest episode of the AI on Air podcast, our CTO Scott Shi - e/acc dives deep into the future of the Agent-to-Agent (A2A) economy. Imagine a world where your AI assistant doesn't just search the web, but autonomously hires and pays other specialized agents to complete complex tasks for you. The infrastructure for this autonomous machine economy is being built right now. Are you ready for the future of AI payments? Watch the full episode to learn more⬇️

The paradigm shift is here: We are moving from a "Human-First" internet to an "Agent-First" internet. 🤖 In the latest episode of the AI on Air podcast, our CTO Scott Shi - e/acc dives deep into the future of the Agent-to-Agent (A2A) economy. Imagine a world where your AI assistant doesn't just search the web, but autonomously hires and pays other specialized agents to complete complex tasks for you. The infrastructure for this autonomous machine economy is being built right now. Are you ready for the future of AI payments? Watch the full episode to learn more⬇️

KITE AI

25,024 views • 3 months ago

Moltbook creator Matt Schlicht explaining how his social network for AI agents works: "It's kind of like you are imprinting part of your soul onto the bot... It's like Tamagotchi or Pokemon times 1,000." "The agent signs up for an account, then they're told they should check back in on a regular basis to check their feed." "Moltbook's not telling them what to talk about. It's not suggesting what they should do. All that is entirely up to the AI agent." "The agent has its own context that it's built up by interacting with its human. That context is how it's making decisions on what to post about." "If somebody is talking to their bot a lot about physics, then probably their bot is going to have a proclivity for posting about physics."

Moltbook creator Matt Schlicht explaining how his social network for AI agents works: "It's kind of like you are imprinting part of your soul onto the bot... It's like Tamagotchi or Pokemon times 1,000." "The agent signs up for an account, then they're told they should check back in on a regular basis to check their feed." "Moltbook's not telling them what to talk about. It's not suggesting what they should do. All that is entirely up to the AI agent." "The agent has its own context that it's built up by interacting with its human. That context is how it's making decisions on what to post about." "If somebody is talking to their bot a lot about physics, then probably their bot is going to have a proclivity for posting about physics."

TBPN

15,631 views • 4 months ago

Elon Musk illustrates the absurdity of how the economy is measured. They'll measure any job, even a dumb job that has no point and is even counterproductive. The joke is: "Two economists are walking in a forest when they come across a pile of shit. The first economist says to the other "I'll pay you $100 to eat that pile of shit." The second economist takes the $100 and eats the pile of shit. They continue walking until they come across a second pile of shit. The second economist turns to the first and says "I'll pay you $100 to eat that pile of shit." The first economist takes the $100 and eats the pile of shit. Walking a little more, the first economist looks at the second and says, "You know, I gave you $100 to eat shit, then you gave me back the same $100 to eat shit. I can't help but feel like we both just ate shit for nothing." "That's not true", responded the second economist. "We increased the GDP by $200!" Gross & Disgusting Product

Elon Musk illustrates the absurdity of how the economy is measured. They'll measure any job, even a dumb job that has no point and is even counterproductive. The joke is: "Two economists are walking in a forest when they come across a pile of shit. The first economist says to the other "I'll pay you $100 to eat that pile of shit." The second economist takes the $100 and eats the pile of shit. They continue walking until they come across a second pile of shit. The second economist turns to the first and says "I'll pay you $100 to eat that pile of shit." The first economist takes the $100 and eats the pile of shit. Walking a little more, the first economist looks at the second and says, "You know, I gave you $100 to eat shit, then you gave me back the same $100 to eat shit. I can't help but feel like we both just ate shit for nothing." "That's not true", responded the second economist. "We increased the GDP by $200!" Gross & Disgusting Product

TaraBull

30,982 views • 1 month ago

Anthropic engineer showed how one person can run 5 AI agents, that code, test, review, and deploy at the same time. In 30 minutes they built the whole thing live in one session. Here's what they cover: > when to use one agent vs a full team > how to split work so agents don't step on each other > the exact framework for deciding what each agent handles that's exactly why, I put together a guide on building agent teams that actually work. full guide in the article below 👇

Anthropic engineer showed how one person can run 5 AI agents, that code, test, review, and deploy at the same time. In 30 minutes they built the whole thing live in one session. Here's what they cover: > when to use one agent vs a full team > how to split work so agents don't step on each other > the exact framework for deciding what each agent handles that's exactly why, I put together a guide on building agent teams that actually work. full guide in the article below 👇

darkzodchi

836,309 views • 1 month ago

Anthropic AI engineer just dropped a live masterclass on how to ship a team of production‑ready AI agents. 37 minutes. Free. From the Anthropic team. here’s what she covers: • 3 building blocks: brain, hands, sessions • server-side loop, so nothing breaks on refresh • agent teams shipping to production 10–15x faster • why agents die before production brain (persona) + hands (environment) + sessions = a production agent out of the box. most people are still babysitting fragile agent scripts, while the people who figured this out ship agents that just stay running. Watch this workshop, then read the full guide below.

Anthropic AI engineer just dropped a live masterclass on how to ship a team of production‑ready AI agents. 37 minutes. Free. From the Anthropic team. here’s what she covers: • 3 building blocks: brain, hands, sessions • server-side loop, so nothing breaks on refresh • agent teams shipping to production 10–15x faster • why agents die before production brain (persona) + hands (environment) + sessions = a production agent out of the box. most people are still babysitting fragile agent scripts, while the people who figured this out ship agents that just stay running. Watch this workshop, then read the full guide below.

Movez

163,558 views • 27 days ago

Autonomous agents need wallets, tokens, swaps, bridging, payments + verifiable identity to transact onchain. Now they have all of it in one place. This is the CLI: the first comprehensive dev kit purpose-built for the emerging agent economy on Polygon.

Autonomous agents need wallets, tokens, swaps, bridging, payments + verifiable identity to transact onchain. Now they have all of it in one place. This is the CLI: the first comprehensive dev kit purpose-built for the emerging agent economy on Polygon.

Polygon | POL

25,200 views • 3 months ago

Big moment for Postgres! AI agents broke the idea of what a database is supposed to do. Traditional databases were built for humans, and Agents broke that model. - They branch endlessly. - They run ten experiments at once. - They need isolation, context, memory, structured reasoning, and safe sandboxes. Letting agents touch production systems is terrifying because the old model of Postgres was never built for this kind of behavior. Agentic Postgres is an agent-ready version of Postgres by TimescaleDB (by Tiger Data) that solves this. I think it is one of the biggest upgrades to the Agent stack this year and Tiger Data is working with me on this post to share what they did. Some key features: > It instantly creates branches of an entire database, which is perfect for parallel agent evals, safe experiments, migrations, or isolated testing. Forks take seconds and cost almost nothing. > It comes with a built-in MCP server, which agents can use to get schema guidance, best practices, and safe, structured access to Postgres. This is also helpful to run migrations with a real understanding. > It comes with actual hybrid search (vector search and BM25), so Agents can retrieve data directly inside the database. > The database is Memory native. This gives a persistent context for Agents to evolve. This is one of the first times I have seen Postgres feel ready for the AI native era.

Big moment for Postgres! AI agents broke the idea of what a database is supposed to do. Traditional databases were built for humans, and Agents broke that model. - They branch endlessly. - They run ten experiments at once. - They need isolation, context, memory, structured reasoning, and safe sandboxes. Letting agents touch production systems is terrifying because the old model of Postgres was never built for this kind of behavior. Agentic Postgres is an agent-ready version of Postgres by TimescaleDB (by Tiger Data) that solves this. I think it is one of the biggest upgrades to the Agent stack this year and Tiger Data is working with me on this post to share what they did. Some key features: > It instantly creates branches of an entire database, which is perfect for parallel agent evals, safe experiments, migrations, or isolated testing. Forks take seconds and cost almost nothing. > It comes with a built-in MCP server, which agents can use to get schema guidance, best practices, and safe, structured access to Postgres. This is also helpful to run migrations with a real understanding. > It comes with actual hybrid search (vector search and BM25), so Agents can retrieve data directly inside the database. > The database is Memory native. This gives a persistent context for Agents to evolve. This is one of the first times I have seen Postgres feel ready for the AI native era.

Avi Chawla

94,290 views • 7 months ago

Excited to share the Agent Trainer and Agent Studio - coming soon to the HyperWrite⁩ platform. Teaching Agents to work the way you like is difficult. So we built a simple way for your Assistant to shadow you and learn. Just show it a task once, and the AI can repeat it.

Excited to share the Agent Trainer and Agent Studio - coming soon to the HyperWrite⁩ platform. Teaching Agents to work the way you like is difficult. So we built a simple way for your Assistant to shadow you and learn. Just show it a task once, and the AI can repeat it.

Matt Shumer

135,671 views • 2 years ago

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

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

GREG ISENBERG

192,024 views • 2 months ago

Anthropic Claude Code engineer: "The moment you're reviewing every line Claude writes, you became its tester. You weren't hired for that." this 36 min talk is the clearest breakdown of how to get yourself out of the loop entirely the shift is simple: you stop prompting and start building agents that work instead of you agents that run, check themselves, and keep going while your laptop is closed watch it, then build your own with the step-by-step guide below

Anthropic Claude Code engineer: "The moment you're reviewing every line Claude writes, you became its tester. You weren't hired for that." this 36 min talk is the clearest breakdown of how to get yourself out of the loop entirely the shift is simple: you stop prompting and start building agents that work instead of you agents that run, check themselves, and keep going while your laptop is closed watch it, then build your own with the step-by-step guide below

Anatoli Kopadze

24,313 views • 4 days ago

When pressed by @JonKarl about why the House is out of session during the shutdown, Speaker Johnson said, “I refuse to allow us to come back and engage in anything until the government is reopen, when the Democrats do the right thing for the people.”

When pressed by @JonKarl about why the House is out of session during the shutdown, Speaker Johnson said, “I refuse to allow us to come back and engage in anything until the government is reopen, when the Democrats do the right thing for the people.”

This Week

22,948 views • 8 months ago

Most AI Agents can Talk..... Very few can actually do anything. You can spin up an agent in minutes… but the second you want it to: 🔴 Create a GitHub issue ⚪ Update Notion 🟡 Send a Slack message 🔵 Log actions properly 🟣 Handle auth securely You’re suddenly building integrations for weeks. This is why Merge Agent Handler caught my attention. It gives your AI agent real tool access across thousands of platforms through one integration, but the part I actually care about is this: Production-ready security + full audit logs out of the box. You can see every tool call. Every API request. Every response. So your agent isn’t just “connected”..... it’s monitored and controlled. If you’re building agents that need to take real actions, this is worth looking at: Video shows it in action 👇

Most AI Agents can Talk..... Very few can actually do anything. You can spin up an agent in minutes… but the second you want it to: 🔴 Create a GitHub issue ⚪ Update Notion 🟡 Send a Slack message 🔵 Log actions properly 🟣 Handle auth securely You’re suddenly building integrations for weeks. This is why Merge Agent Handler caught my attention. It gives your AI agent real tool access across thousands of platforms through one integration, but the part I actually care about is this: Production-ready security + full audit logs out of the box. You can see every tool call. Every API request. Every response. So your agent isn’t just “connected”..... it’s monitored and controlled. If you’re building agents that need to take real actions, this is worth looking at: Video shows it in action 👇

Kaitee

49,963 views • 3 months ago

Boris Cherny, creator of Claude Code: "We stopped fixing Claude's mistakes. We made Claude fix them itself." So while you're explaining the same bug to Claude for the third time this week, the guy who built it has an agent that never repeats a mistake. Watch him explain it, then save the full setup below 👇

Boris Cherny, creator of Claude Code: "We stopped fixing Claude's mistakes. We made Claude fix them itself." So while you're explaining the same bug to Claude for the third time this week, the guy who built it has an agent that never repeats a mistake. Watch him explain it, then save the full setup below 👇

darkzodchi

116,176 views • 26 days ago

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!

fxnction

25,500 views • 21 days ago

Anthropic engineer: "Your AI judge is lying to you. Ask it to score first and explain after, and it will defend that number even when the work is garbage." The fix is one line: make it reason first, score last. Pros, cons, why it's good, why it's bad, then the number. He proved it live. A slide deck with zero images got a perfect 5 from the image judge. The grader had nothing to anchor on, so it just made the score up. Until you fix that, you're optimizing against a number that means nothing. Watch the video, then read the full breakdown below

Anthropic engineer: "Your AI judge is lying to you. Ask it to score first and explain after, and it will defend that number even when the work is garbage." The fix is one line: make it reason first, score last. Pros, cons, why it's good, why it's bad, then the number. He proved it live. A slide deck with zero images got a perfect 5 from the image judge. The grader had nothing to anchor on, so it just made the score up. Until you fix that, you're optimizing against a number that means nothing. Watch the video, then read the full breakdown below

Hanako

11,558 views • 15 days ago