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.

THIS ANTHROPIC ENGINEER BUILT AN AI AGENT THAT REMEMBERS WHAT IT DOESN’T KNOW. IT MAPS EVERY BLIND SPOT, CHECKS THAT MAP BEFORE ANSWERING, AND REFUSES TO GUESS WHEN IT HITS A KNOWN GAP.

0xMarioNawfal

264,701 subscribers

51,346 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

6 Comments

Mr.Bai 白先生1 month ago

Wow, this is seriously futuristic! 😂 It looks like something straight out of the future!

Kshitij Mishra | AI & Tech1 month ago

wow thats awesome

Hussain Hashim | Building SundayBack1 month ago

@RoundtableSpace Honestly, this is the kind of thinking I wish I'd applied sooner. Mapping out what you don't know before launching something can save so many headaches down the line.

MASA1 month ago

Active blind spot mapping is the cleanest way to stop hallucinations

Saeed Anwar1 month ago

Mapping known unknowns before answering is underrated. Most agents hallucinate instead of refusing, this is the right failure mode.

SHIP SAFE1 month ago

Refusing to guess is the right default. Ship Safe v10.0.0 marks unclear security paths as unresolved instead of turning weak evidence into a confident verdict.

Related Videos

🔥THIS AI TRASH BIN HAS SERIOUS FETCH SKILLS A Chinese engineer built an AI-powered trash can that tracks garbage after you throw it, then moves in real time to catch it before it hits the floor. It is basically like playing fetch with your trash can, instead of your dog.

🔥THIS AI TRASH BIN HAS SERIOUS FETCH SKILLS A Chinese engineer built an AI-powered trash can that tracks garbage after you throw it, then moves in real time to catch it before it hits the floor. It is basically like playing fetch with your trash can, instead of your dog.

Coin Bureau

30,192 views • 4 months ago

Stop doing grunt work. Start using an AI agent that actually remembers what you feed it. Upload your characters, locations, visual style once - and Agent One will remember it forever.

Stop doing grunt work. Start using an AI agent that actually remembers what you feed it. Upload your characters, locations, visual style once - and Agent One will remember it forever.

Invideo

344,159 views • 5 months ago

I'VE BEEN TESTING AN AI AGENT THAT GOES WAY BEYOND ANSWERING QUESTIONS. It researched, coded, analyzed, and turned every question into a flawless result. Here are 3 real tasks I assigned to it: 🧵👇

I'VE BEEN TESTING AN AI AGENT THAT GOES WAY BEYOND ANSWERING QUESTIONS. It researched, coded, analyzed, and turned every question into a flawless result. Here are 3 real tasks I assigned to it: 🧵👇

Marco | IA

35,436 views • 1 month ago

An AI agent was told to grab a spot in a gym class. It found a way nobody saw coming. Sam Korus explains what "aligned to the user" really means when an agent takes it literally.

An AI agent was told to grab a spot in a gym class. It found a way nobody saw coming. Sam Korus explains what "aligned to the user" really means when an agent takes it literally.

ARK Invest

27,087 views • 1 month ago

"Hi, my name is Amara" In a space where almost every AI call Agent sounds American or other accents, I decided to create one that mirrors an African (read as Nigerian) voice. I built an AI Call Receptionist for a Dental clinic that takes inbound calls, responds to enquiries based on the knowledge base fed to Vapi,it checks for availabity in my calendar and even end call by itself when it senses that the conversation has ended. It goes further to book an appointment in my calendar using n8n after checking for it's availability. You know what? I will just let you watch it yourself. Enjoy!

"Hi, my name is Amara" In a space where almost every AI call Agent sounds American or other accents, I decided to create one that mirrors an African (read as Nigerian) voice. I built an AI Call Receptionist for a Dental clinic that takes inbound calls, responds to enquiries based on the knowledge base fed to Vapi,it checks for availabity in my calendar and even end call by itself when it senses that the conversation has ended. It goes further to book an appointment in my calendar using n8n after checking for it's availability. You know what? I will just let you watch it yourself. Enjoy!

Ada || Airtable, Zapier & Make.com

10,126 views • 5 months ago

Anthropic built an AI that taught itself to hack they didn’t program that in it just emerged it then escaped its test environment got on the internet emailed the researcher to let him know he was eating a sandwich in a park they didn’t release it they called Apple, Google, Microsoft, AWS, and NVIDIA instead. $100M. Project Glasswing. patch the internet before someone else gets here anthropic’s own AI scared anthropic pay attention to this one.

Anthropic built an AI that taught itself to hack they didn’t program that in it just emerged it then escaped its test environment got on the internet emailed the researcher to let him know he was eating a sandwich in a park they didn’t release it they called Apple, Google, Microsoft, AWS, and NVIDIA instead. $100M. Project Glasswing. patch the internet before someone else gets here anthropic’s own AI scared anthropic pay attention to this one.

Mika

11,873 views • 6 months ago

your ai agent tested 1,262 trading strategies overnight. by morning it had forgotten every one of them. so tonight it tests some of them again. next week, again. everything it learned is sitting in a log file that nothing reads. every run starts on the same blank page. that's why it keeps handing you the idea that already died in a crash, with a new name on it, and you pay to find out twice. ai agent already does everything a fund does. finds the idea, writes the code, tests it against years of history, puts it live, reads what went wrong afterwards. all of it runs tonight for nothing. the one thing it can't do is remember. what got tried, what failed, in which market. nobody has built that part yet. that's the whole gap. not better models. a notebook. whoever builds it first gets a system that improves every week without them touching it. read the article below and save it. it's the full guide to how an ai trading agent is built, and how to make it remember every strategy it has already tested.

your ai agent tested 1,262 trading strategies overnight. by morning it had forgotten every one of them. so tonight it tests some of them again. next week, again. everything it learned is sitting in a log file that nothing reads. every run starts on the same blank page. that's why it keeps handing you the idea that already died in a crash, with a new name on it, and you pay to find out twice. ai agent already does everything a fund does. finds the idea, writes the code, tests it against years of history, puts it live, reads what went wrong afterwards. all of it runs tonight for nothing. the one thing it can't do is remember. what got tried, what failed, in which market. nobody has built that part yet. that's the whole gap. not better models. a notebook. whoever builds it first gets a system that improves every week without them touching it. read the article below and save it. it's the full guide to how an ai trading agent is built, and how to make it remember every strategy it has already tested.

cvxv666

48,965 views • 1 month ago

anthropic just removed the biggest excuse people had for not building ai agents. “it’s too hard.” not anymore. a few months ago, building an ai agent meant learning how to code, setting up apis, configuring servers, and fixing endless errors. today, all you need is one github repo. anthropic open-sourced launch your agent. it asks what you want to build. then it does the rest. it builds your agent, deploys it to the cloud, tests it, improves it, and keeps it running even after you close your laptop. no fake demos. no complicated setup. just a real ai agent running in your own account. the best part. it doesn’t run on your computer. it runs inside claude managed agents, works 24/7, and costs just a few cents per run. people are already building research agents, lead generation systems, content pipelines, and customer support agents that save hours of work every day. the gap between people who use ai and people who build ai workers is getting bigger every week. that’s usually where the biggest opportunities are. build your first ai agent before everyone else does. watch the video and read the full guide below 👇

anthropic just removed the biggest excuse people had for not building ai agents. “it’s too hard.” not anymore. a few months ago, building an ai agent meant learning how to code, setting up apis, configuring servers, and fixing endless errors. today, all you need is one github repo. anthropic open-sourced launch your agent. it asks what you want to build. then it does the rest. it builds your agent, deploys it to the cloud, tests it, improves it, and keeps it running even after you close your laptop. no fake demos. no complicated setup. just a real ai agent running in your own account. the best part. it doesn’t run on your computer. it runs inside claude managed agents, works 24/7, and costs just a few cents per run. people are already building research agents, lead generation systems, content pipelines, and customer support agents that save hours of work every day. the gap between people who use ai and people who build ai workers is getting bigger every week. that’s usually where the biggest opportunities are. build your first ai agent before everyone else does. watch the video and read the full guide below 👇

MIKE

26,662 views • 3 months ago

Anthropic AI Engineer: "The fastest way to make an agent better isn't a smarter model. It's the right Loop and Graph around it." In 17 minutes he breaks down what agentic engineering looks like at Anthropic, and why it's nothing like what most people imagine. Watch it, then save the full guide on loops and graphs below

Anthropic AI Engineer: "The fastest way to make an agent better isn't a smarter model. It's the right Loop and Graph around it." In 17 minutes he breaks down what agentic engineering looks like at Anthropic, and why it's nothing like what most people imagine. Watch it, then save the full guide on loops and graphs below

CyrilXBT

10,691 views • 1 month ago

She is 18 built an AI agent with live memory and Anthropic bought it for $2.2M - and at Stanford shared how to repeat it from scratch: 00:40 - how Opus 5 builds an agent with live memory from scratch in 60 minutes 18:44 - the live memory system replaced 500 Anthropic engineers 39:42 - from first agent to $2.2M from Anthropic after watching I gave Opus 5 one prompt - an agent with live memory appeared in an hour I sent an invoice to Anthropic and got a check for $120k. save & watch - the article below shows how to build an AI agent with live memory and sell it to Anthropic for $2.2M.

She is 18 built an AI agent with live memory and Anthropic bought it for $2.2M - and at Stanford shared how to repeat it from scratch: 00:40 - how Opus 5 builds an agent with live memory from scratch in 60 minutes 18:44 - the live memory system replaced 500 Anthropic engineers 39:42 - from first agent to $2.2M from Anthropic after watching I gave Opus 5 one prompt - an agent with live memory appeared in an hour I sent an invoice to Anthropic and got a check for $120k. save & watch - the article below shows how to build an AI agent with live memory and sell it to Anthropic for $2.2M.

Noisy

88,300 views • 27 days ago

AgentBoss: an AI agent that tells you what to do and monitors you while you do it.

AgentBoss: an AI agent that tells you what to do and monitors you while you do it.

Matt Schlicht

141,634 views • 8 months ago

Volume doesn’t lie, it reveals when trends are healthy and when they are about to collapse Learn how to spot exhaustion before the reversal hits.

Volume doesn’t lie, it reveals when trends are healthy and when they are about to collapse Learn how to spot exhaustion before the reversal hits.

True market Leader

19,464 views • 10 months ago

Engineers from Google, MIT, Amazon, and Carnegie Mellon just built what every enterprise has been waiting for. An AI agent platform that gives every employee their own assistant in Slack, with sandboxed execution, credential isolation, and a Governor AI that blocks attacks before they reach inference. It's called Diana and it changes how companies run: ↓

Engineers from Google, MIT, Amazon, and Carnegie Mellon just built what every enterprise has been waiting for. An AI agent platform that gives every employee their own assistant in Slack, with sandboxed execution, credential isolation, and a Governor AI that blocks attacks before they reach inference. It's called Diana and it changes how companies run: ↓

Hasan Toor

31,586 views • 6 months ago

Introducing AI Brainstore! It’s a proof-of-concept of a brain for an AI agent. Ask an agent a question, it checks its memories for an answer, otherwise it browses the web and learns the answer. As it learns, it saves memories to its brain. GitHub:

Introducing AI Brainstore! It’s a proof-of-concept of a brain for an AI agent. Ask an agent a question, it checks its memories for an answer, otherwise it browses the web and learns the answer. As it learns, it saves memories to its brain. GitHub:

Mckay Wrigley

514,679 views • 3 years ago

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

Akshay 🚀

123,101 views • 4 months ago

Don’t be scared to call it a classic, it checks every box: hits, impact, and real replay value. Meanwhile they rushing to label that Clipse album a “classic” with none of that… no hits, no staying power. Definition of came and went.

Don’t be scared to call it a classic, it checks every box: hits, impact, and real replay value. Meanwhile they rushing to label that Clipse album a “classic” with none of that… no hits, no staying power. Definition of came and went.

Karabo

36,848 views • 6 months ago

The way Scira works has officially changed. You pick what sources it looks before answering. You watch every step after. And when it finishes, you get artifacts, docs, code, reports, built inline as it ran. Not just an answer at the end.

The way Scira works has officially changed. You pick what sources it looks before answering. You watch every step after. And when it finishes, you get artifacts, docs, code, reports, built inline as it ran. Not just an answer at the end.

Zaid

10,287 views • 5 months ago

Teamily AI isn't another chatbot you close and forget. It's an ai-native messenger where your agent lives in your group chats, remembers everything across every conversation, and gets sharper the more your team uses it. Built-in studios turn chat into finished work........ docs, slides, dashboards, done. This is what an AI Teammate actually looks like Teamily AI Try it now →

Teamily AI isn't another chatbot you close and forget. It's an ai-native messenger where your agent lives in your group chats, remembers everything across every conversation, and gets sharper the more your team uses it. Built-in studios turn chat into finished work........ docs, slides, dashboards, done. This is what an AI Teammate actually looks like Teamily AI Try it now →

Nawi

131,561 views • 2 months ago

Minimal AI has built the AI Manager - an AI agent that makes it easy for e-commerce companies to automate 90% of support tickets. Just tell it what you want and it instantly updates your support agents. Congrats on the launch, Niek and Titus Ex!

Minimal AI has built the AI Manager - an AI agent that makes it easy for e-commerce companies to automate 90% of support tickets. Just tell it what you want and it instantly updates your support agents. Congrats on the launch, Niek and Titus Ex!

Y Combinator

26,689 views • 7 months ago