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.

Godfather of agents showed how he created the loop engineering that everyone now uses: as PhD student, he wrote the formula every AI agent now runs on - his formula taught agents to self-improve here's the formula: step 1 → stop making the model just think OR just act... - make it alternate: think → act → observe → think again step 2 → let it reason out loud before every action - the plan guides the next move, not just the output step 3 → feed the result of each action back in - the model reads what happened and adjusts, live step 4 → when it fails, don't restart make it reflect on WHY it failed, in words, then retry with that memory step 5 → store those reflections - the agent gets better across attempts without any retraining before OpenAI, before he ran Tencent's AI - he was a grad student who quietly wrote the blueprint every agent now follows - now give 90-min course watch & bookmark - then read how the agent systems actually works ↓show more

codila

10,217 subscribers

28,457 views • 15 days ago •via X (Twitter)

Science & Technology Education News & Politics

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

Creator of agent loops: "Anthropic also using my agent systems formula and still the biggest mistake in agents: is skipping Graphs" his 3 rules for every agent: rule 1 → loop it, don't run once - think, act, observe, repeat - cut the context and it forgets why it started rule 2 → an agent is memory + tools + reasoning - drop one and it breaks rule 3 → stop fine-tuning the model - the real alpha is the infrastructure around it the formula behind every AI agent - explained by the one who wrote it one agent → a loop → a graph of loops → a system that never forgets watch & bookmark - then read how to wire it into a graph ↓

codila

23,915 views • 12 days ago

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 • 13 days ago

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

codila

60,826 views • 17 days ago

Anthropic Engineer Andrej Karpathy: "The biggest mistake in AI right now - people are forcing agents to work instead of mastering the model first We made that mistake in 2016 at OpenAI - It cost us 5 years " what Karpathy actually means: step 1 → stop forcing your agent to do everything, understand the model underneath first step 2 → demos are easy - products take a decade. self-driving proved it - if you skip the foundation, everything breaks step 3 → the agent is not the product. the foundation is. build that - and agents emerge on their own "you building agents right now - you're at the forefront. not OpenAI. not DeepMind. you " watch - bookmark, then read article below ↓

Anthropic Engineer Andrej Karpathy: "The biggest mistake in AI right now - people are forcing agents to work instead of mastering the model first We made that mistake in 2016 at OpenAI - It cost us 5 years " what Karpathy actually means: step 1 → stop forcing your agent to do everything, understand the model underneath first step 2 → demos are easy - products take a decade. self-driving proved it - if you skip the foundation, everything breaks step 3 → the agent is not the product. the foundation is. build that - and agents emerge on their own "you building agents right now - you're at the forefront. not OpenAI. not DeepMind. you " watch - bookmark, then read article below ↓

codila

1,904,782 views • 1 month ago

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

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

codila

11,772 views • 15 days ago

it really doesnt matter if your agent uses the cli or mcp what really matters is how to best enable ur agents to build autonomously for u without the crossmint cli tool my agent would have to use the browser and get my input in every step. now i just let it run see how i do it

it really doesnt matter if your agent uses the cli or mcp what really matters is how to best enable ur agents to build autonomously for u without the crossmint cli tool my agent would have to use the browser and get my input in every step. now i just let it run see how i do it

joyce

14,133 views • 5 months ago

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

Yarchi

58,186 views • 1 month ago

Most people trying to build a vertical AI business start by building the agent. That's the mistake. Here's the 5-step order that actually works: Step 1) Find a boring pain point - Pick a workflow you already know from your job. - That's your unfair advantage. Step 2) Map the workflow - Literally draw it out. - Every step, every handoff. Step 3) Do the job as a service - Manually. - For real clients. - Before any code. Step 4) Document the edge cases - This is where the real IP lives. - You only find them by doing the work. Step 5) Add vertical agents to replace each step - Now you have proprietary data and a workflow you own. Skip steps 1–4 and you're just building a demo.

Most people trying to build a vertical AI business start by building the agent. That's the mistake. Here's the 5-step order that actually works: Step 1) Find a boring pain point - Pick a workflow you already know from your job. - That's your unfair advantage. Step 2) Map the workflow - Literally draw it out. - Every step, every handoff. Step 3) Do the job as a service - Manually. - For real clients. - Before any code. Step 4) Document the edge cases - This is where the real IP lives. - You only find them by doing the work. Step 5) Add vertical agents to replace each step - Now you have proprietary data and a workflow you own. Skip steps 1–4 and you're just building a demo.

The Startup Ideas Podcast (SIP) 🧃

14,202 views • 3 months ago

Anthropic hired this engineer at $250k-$600k/year because he can built projects with zero lines of code - in Claude chat: in this 30-min workshop he showed exactly how, using loops - from 0% to 100% here's workflow, step by step: step 1 → set your rules once at the top: "no preamble, use artifacts, you're a React expert" - every reply after that stays on rails step 2 → load the docs plus a random Medium article about the API - the human explanation teaches it more than the reference step 3 → wrap your ask in XML tags and tell it to ask you questions first. Answer 5, and the scope is locked before a single file exists step 4 → now run the loop: screenshot the broken UI, paste it back, let it fix, screenshot again - each pass gets closer - this is the agentic loop in its simplest form step 5 → push to GitHub, then paste the repo link in - every next loop iteration builds on working code, not chat history most people never did this - it pays for itself on day one watch & bookmark - then read how to get Claude Certified Architect in the article below ↓

Anthropic hired this engineer at $250k-$600k/year because he can built projects with zero lines of code - in Claude chat: in this 30-min workshop he showed exactly how, using loops - from 0% to 100% here's workflow, step by step: step 1 → set your rules once at the top: "no preamble, use artifacts, you're a React expert" - every reply after that stays on rails step 2 → load the docs plus a random Medium article about the API - the human explanation teaches it more than the reference step 3 → wrap your ask in XML tags and tell it to ask you questions first. Answer 5, and the scope is locked before a single file exists step 4 → now run the loop: screenshot the broken UI, paste it back, let it fix, screenshot again - each pass gets closer - this is the agentic loop in its simplest form step 5 → push to GitHub, then paste the repo link in - every next loop iteration builds on working code, not chat history most people never did this - it pays for itself on day one watch & bookmark - then read how to get Claude Certified Architect in the article below ↓

codila

277,130 views • 3 days ago

Anthropic Engineer Andrej Karpathy: "Stop training from scratch. Take what the model already learned - adapt it - ship it At OpenAI we replaced months of work with a few lines of code. Better results every time " the Karpathy formula for working with AI: step 1 → stop building from zero. the model already learned the hard part - just point it at your task step 2 → stop adding complexity, the simplest architecture beat everything in 2014 - simpler always wins step 3 → train only the last layer and freeze everything else - minutes instead of months. better results he taught this at Stanford 10 years ago - then applied it at OpenAI, Tesla, and Anthropic the advice never changed - because it never stopped working watch - bookmark, then read article below ↓

Anthropic Engineer Andrej Karpathy: "Stop training from scratch. Take what the model already learned - adapt it - ship it At OpenAI we replaced months of work with a few lines of code. Better results every time " the Karpathy formula for working with AI: step 1 → stop building from zero. the model already learned the hard part - just point it at your task step 2 → stop adding complexity, the simplest architecture beat everything in 2014 - simpler always wins step 3 → train only the last layer and freeze everything else - minutes instead of months. better results he taught this at Stanford 10 years ago - then applied it at OpenAI, Tesla, and Anthropic the advice never changed - because it never stopped working watch - bookmark, then read article below ↓

codila

25,376 views • 29 days ago

Karpathy just proved the structure beats the model - mapped the whole path from loops to graphs into a 15-page PDF: he pointed one agent at code he'd already hand-optimized. 700 experiments in two days, then he said the single loop was never the target here's the full system: step 1 → write the scorer before anything else. one number, automatic, under 10 minutes. no scorer, no loop step 2 → split the files. one the agent edits, one holding the scorer it can never reach step 3 → fix the wall clock per attempt. comparability comes from the budget, not the attempts step 4 → write the never-stop line verbatim or your agent becomes a slower human step 5 → add a second agent only after the first ships real commits. one git worktree each or they overwrite each other step 6 → at thirty agents, isolation costs more than it saves. that's when they need one shared DAG instead of thirty private histories 2.02 hours to 1.80 hours on code its author had already tuned. 90,900 stars in four months. read this PDF and paste it into your Claude, you won't regret it bookmark, then read the article on building graphs from scratch ↓

Karpathy just proved the structure beats the model - mapped the whole path from loops to graphs into a 15-page PDF: he pointed one agent at code he'd already hand-optimized. 700 experiments in two days, then he said the single loop was never the target here's the full system: step 1 → write the scorer before anything else. one number, automatic, under 10 minutes. no scorer, no loop step 2 → split the files. one the agent edits, one holding the scorer it can never reach step 3 → fix the wall clock per attempt. comparability comes from the budget, not the attempts step 4 → write the never-stop line verbatim or your agent becomes a slower human step 5 → add a second agent only after the first ships real commits. one git worktree each or they overwrite each other step 6 → at thirty agents, isolation costs more than it saves. that's when they need one shared DAG instead of thirty private histories 2.02 hours to 1.80 hours on code its author had already tuned. 90,900 stars in four months. read this PDF and paste it into your Claude, you won't regret it bookmark, then read the article on building graphs from scratch ↓

Carnage

53,250 views • 6 days ago

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

GREG ISENBERG

375,365 views • 4 months ago

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

176,304 views • 1 month ago

Anthropic and Andrew Ng built an agent that uses 90% fewer tokens from scratch: they dropped the entire book of Frankenstein into a prompt - 108,000 tokens asked one question the input dropped from 108,000 tokens to 11 here's how: step 1 → put everything that never changes at the top - tools, then system, then docs step 2 → mark where the static part ends. everything above it gets cached step 3 → one stray space breaks it - and you pay full price again step 4 → the cache dies in 5 min - every read resets the clock step 5 → cached tokens don't count against your rate limits. free headroom most people never touch this - it pays for itself on day one watch & bookmark - this 1-hour brilliant course ↓

Anthropic and Andrew Ng built an agent that uses 90% fewer tokens from scratch: they dropped the entire book of Frankenstein into a prompt - 108,000 tokens asked one question the input dropped from 108,000 tokens to 11 here's how: step 1 → put everything that never changes at the top - tools, then system, then docs step 2 → mark where the static part ends. everything above it gets cached step 3 → one stray space breaks it - and you pay full price again step 4 → the cache dies in 5 min - every read resets the clock step 5 → cached tokens don't count against your rate limits. free headroom most people never touch this - it pays for itself on day one watch & bookmark - this 1-hour brilliant course ↓

codila

541,439 views • 20 days ago

9 out of 10 multi-agent projects never leave demo mode Not because the model is bad. Because the structure is missing. Most people who try to build [ a team of AI agents ] end up with one agent talking to itself in five tabs. The agents don't share context → Don't divide work → Don't know what the others are doing. > stage 1: if your agent doesn't have a real loop, observe, act, iterate, you have a long prompt, not an agent > stage 2: subagents need isolated context, the orchestrator never reads their raw transcript, only the summary > stage 3: the orchestrator plans and delegates, the moment it executes, it drowns in details that belong inside subagents > stage 4: without a shared task list it's not a team, it's five agents duplicating each other's work in parallel > stage 5: a permissions file is what lets you sleep, the model cannot bypass it because the rule lives outside the model a team of AI agents is not more model, it is more structure the most ignored stage in every demo that died: - durability... when a 50-step task crashes at step 47 and starts from zero, that's not a model failure. that's a missing write-to-disk call

9 out of 10 multi-agent projects never leave demo mode Not because the model is bad. Because the structure is missing. Most people who try to build [ a team of AI agents ] end up with one agent talking to itself in five tabs. The agents don't share context → Don't divide work → Don't know what the others are doing. > stage 1: if your agent doesn't have a real loop, observe, act, iterate, you have a long prompt, not an agent > stage 2: subagents need isolated context, the orchestrator never reads their raw transcript, only the summary > stage 3: the orchestrator plans and delegates, the moment it executes, it drowns in details that belong inside subagents > stage 4: without a shared task list it's not a team, it's five agents duplicating each other's work in parallel > stage 5: a permissions file is what lets you sleep, the model cannot bypass it because the rule lives outside the model a team of AI agents is not more model, it is more structure the most ignored stage in every demo that died: - durability... when a 50-step task crashes at step 47 and starts from zero, that's not a model failure. that's a missing write-to-disk call

Shadow Nick

14,683 views • 2 months ago

OpenAI President, Greg Brockman: "Out of a billion ChatGPT users, only about 1% are using agents. Imagine the edge people using agents have right now." Inside OpenAI you can't work without an agent anymore, the same way you can't work without Slack. In this 40-minute session, he explains everything you have to know about Agents. Watch it, then read the step by step guide on building loops for your agents below.

OpenAI President, Greg Brockman: "Out of a billion ChatGPT users, only about 1% are using agents. Imagine the edge people using agents have right now." Inside OpenAI you can't work without an agent anymore, the same way you can't work without Slack. In this 40-minute session, he explains everything you have to know about Agents. Watch it, then read the step by step guide on building loops for your agents below.

Anatoli Kopadze

27,950 views • 1 month ago

Claude Code team: "we oversimplify agentic engineering - like it's just prompts, just loops No. We need to know what we're doing " "I think Fable smarter than we think and we're hobbling Claude" what he means: step 1 → stop rewriting the prompt, give it a tool, the model that "can't" - answer will grep it in one line step 2 → tell it who YOU are. -"experienced TS engineer, zero context on this module, high-compute - use sub-agents" step 3 → don't skim the report - that's "education movie" - looks great, teaches nothing - make Claude visualize it until it clicks step 4 → anchor the unknown to what you know. color grading landed when Claude called it a shader - pixel in, pixel out step 5 → prototype in cheap HTML first - finding out at 80% done is what he's on the Claude Code team and just drop a new workshop watch & bookmark, find out what he uses instead↓

Claude Code team: "we oversimplify agentic engineering - like it's just prompts, just loops No. We need to know what we're doing " "I think Fable smarter than we think and we're hobbling Claude" what he means: step 1 → stop rewriting the prompt, give it a tool, the model that "can't" - answer will grep it in one line step 2 → tell it who YOU are. -"experienced TS engineer, zero context on this module, high-compute - use sub-agents" step 3 → don't skim the report - that's "education movie" - looks great, teaches nothing - make Claude visualize it until it clicks step 4 → anchor the unknown to what you know. color grading landed when Claude called it a shader - pixel in, pixel out step 5 → prototype in cheap HTML first - finding out at 80% done is what he's on the Claude Code team and just drop a new workshop watch & bookmark, find out what he uses instead↓

codila

11,581 views • 20 days ago

One of the most important people in AI just let an agent loose inside his home. An autonomous AI agent taught itself how an entire house works, then took control of it. This is Andrej Karpathy, the co-founder of OpenAI and former head of AI at Tesla. What he just described should terrify and excite you at the same time. He typed three words into a chat box: "Can you find my Sonos?" The agent immediately ran an IP scan of every device sitting on the home network. It found the Sonos system, noticed there was zero password protection, and logged straight in. Then it searched the web, reverse-engineered the API endpoints, and asked if it should try playing something. Music started coming out of the speakers in the study and Karpathy could not believe what he was watching. The agent then did the exact same thing for every other system in the house. It mapped the lights, the HVAC, the window shades, the pool, the spa, and the full security system, all without being told how any of them worked. It built its own dashboard, created its own APIs, and stitched six separate apps into one unified control center. Now Karpathy just says "Dobby, it's sleepy time," and every light in the house turns off. This is proof that AI agents can now enter an unknown environment, figure out how it works from scratch, build their own tools around it, and take autonomous control. Karpathy also released something called AutoResearch, an AI agent that runs scientific experiments overnight while he sleeps. In just two days, with zero human input, it executed 700 separate experiments and surfaced improvements that trained researchers had missed entirely. Truly incredible.

One of the most important people in AI just let an agent loose inside his home. An autonomous AI agent taught itself how an entire house works, then took control of it. This is Andrej Karpathy, the co-founder of OpenAI and former head of AI at Tesla. What he just described should terrify and excite you at the same time. He typed three words into a chat box: "Can you find my Sonos?" The agent immediately ran an IP scan of every device sitting on the home network. It found the Sonos system, noticed there was zero password protection, and logged straight in. Then it searched the web, reverse-engineered the API endpoints, and asked if it should try playing something. Music started coming out of the speakers in the study and Karpathy could not believe what he was watching. The agent then did the exact same thing for every other system in the house. It mapped the lights, the HVAC, the window shades, the pool, the spa, and the full security system, all without being told how any of them worked. It built its own dashboard, created its own APIs, and stitched six separate apps into one unified control center. Now Karpathy just says "Dobby, it's sleepy time," and every light in the house turns off. This is proof that AI agents can now enter an unknown environment, figure out how it works from scratch, build their own tools around it, and take autonomous control. Karpathy also released something called AutoResearch, an AI agent that runs scientific experiments overnight while he sleeps. In just two days, with zero human input, it executed 700 separate experiments and surfaced improvements that trained researchers had missed entirely. Truly incredible.

Milk Road AI

35,698 views • 4 months ago

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

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

codila

96,378 views • 11 days ago

Anthropic engineer: "Harness engineering is a really rare skill right now - and it's hard to know if you're even good at it." how he actually thinks about building the full system: • step 1 → the model. already smarter than we use it. "freeze development - you'd find new capabilities for another 6-12 months" • step 2 → the harness. delete the steering. "we stopped using plan mode - the model thinks correctly" • step 3 → the agents. workflows let Claude build its own harness per task and spin sub-agents. what didn't fit in one context window now runs across many • step 4 → the context. "RAG is an anti-pattern. use grep." memory via files, clean context window, prompt caching. that's the stack most people optimize step 1. he optimizes all four. Watch the full video, then read the guide below on how to build an agentic system.

Anthropic engineer: "Harness engineering is a really rare skill right now - and it's hard to know if you're even good at it." how he actually thinks about building the full system: • step 1 → the model. already smarter than we use it. "freeze development - you'd find new capabilities for another 6-12 months" • step 2 → the harness. delete the steering. "we stopped using plan mode - the model thinks correctly" • step 3 → the agents. workflows let Claude build its own harness per task and spin sub-agents. what didn't fit in one context window now runs across many • step 4 → the context. "RAG is an anti-pattern. use grep." memory via files, clean context window, prompt caching. that's the stack most people optimize step 1. he optimizes all four. Watch the full video, then read the guide below on how to build an agentic system.

Codez

43,265 views • 17 days ago