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 Andrej Karpathy: "LLM models writes code - and now it writes it better than you." Now LLMs write 70–90% of production code at top AI labs. Agents need the same thing: a loop that verifies its own output. No baseline = no benchmark = no improvement. In... show more

Ricker

8,182 subscribers

11,308 views • 6 days 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

Andrej Karpathy just said what no one wants to admit: "Your agent loop is generating garbage at scale and you can't see it." 1 output looks fine. 1,000 outputs = dead entropy, dead diversity. 90% of AI companies are building demos, not products. In a 20-minute conversation, Karpathy reveals the full reasoning stack

Andrej Karpathy just said what no one wants to admit: "Your agent loop is generating garbage at scale and you can't see it." 1 output looks fine. 1,000 outputs = dead entropy, dead diversity. 90% of AI companies are building demos, not products. In a 20-minute conversation, Karpathy reveals the full reasoning stack

Ricker

311,316 views • 11 days ago

Anthropic Developer Andrej Karpathy: "At OpenAI I saw two types of engineers: ones who write every instruction - ones who describe what they want The second type replaced the first in a year " the Karpathy framework - 3 eras of programming: 1.0 → you write the code → takes weeks 2.0 → you feed data, model writes the algorithm → takes hours 3.0 → you describe what you want in English → takes minutes each era killed the last. most people are still in 1.0 "the best code is the code you never write. you don't program the solution - you program the data -the solution programs itself" he built this at OpenAI - now applies it at Anthropic - the framework never changed watch & save - guide about Software by Andrej ↓

Anthropic Developer Andrej Karpathy: "At OpenAI I saw two types of engineers: ones who write every instruction - ones who describe what they want The second type replaced the first in a year " the Karpathy framework - 3 eras of programming: 1.0 → you write the code → takes weeks 2.0 → you feed data, model writes the algorithm → takes hours 3.0 → you describe what you want in English → takes minutes each era killed the last. most people are still in 1.0 "the best code is the code you never write. you don't program the solution - you program the data -the solution programs itself" he built this at OpenAI - now applies it at Anthropic - the framework never changed watch & save - guide about Software by Andrej ↓

codila

106,546 views • 22 days ago

Anthropic just paid millions to hire Andrej Karpathy. He gave you the same knowledge for $0 the same week. Co-founder of OpenAI. Former head of AI at Tesla. The man who coined vibe coding. No recruitment fee. No exclusive access. Just a link and 29 minutes. LLMs are ghosts not animals. Vibe coding is dead. Software 3.0 is here. Watch it. Then read this. Because Karpathy tells you what Software 3.0 is. This shows you how to build one - a software factory with Claude Code that ships features while you sleep. The full build guide is below.

Anthropic just paid millions to hire Andrej Karpathy. He gave you the same knowledge for $0 the same week. Co-founder of OpenAI. Former head of AI at Tesla. The man who coined vibe coding. No recruitment fee. No exclusive access. Just a link and 29 minutes. LLMs are ghosts not animals. Vibe coding is dead. Software 3.0 is here. Watch it. Then read this. Because Karpathy tells you what Software 3.0 is. This shows you how to build one - a software factory with Claude Code that ships features while you sleep. The full build guide is below.

Rahul

1,202,114 views • 2 months ago

Anthropic Quant Andrej Karpathy: "Most people use tools that they don't understand - the ones who strip everything down to basics - end up faster than everyone else " "the best code is the code anyone can read " he couldn't fix a bug in 2 hours, so instead of googling - he rewrote the entire system from scratch no frameworks. no dependencies. it ended up faster that's the difference between using AI and understanding it 25-min masterclass - bookmark and watch

Anthropic Quant Andrej Karpathy: "Most people use tools that they don't understand - the ones who strip everything down to basics - end up faster than everyone else " "the best code is the code anyone can read " he couldn't fix a bug in 2 hours, so instead of googling - he rewrote the entire system from scratch no frameworks. no dependencies. it ended up faster that's the difference between using AI and understanding it 25-min masterclass - bookmark and watch

codila

378,849 views • 1 month ago

My friend makes $850,000/year as an Anthropic AI engineer. No MIT. No Stanford. No PhD. I asked him how he broke into AI from scratch. He sent me a course that was never supposed to get out. A developer teaching to build self-improving AI agents from scratch. You will learn exactly how AI agents like Claude Code and OpenClaw are actually built. You won't find anything better about becoming an AI engineer in 2026 than this video. I watched it last night. Halfway through, I realized I could land a role at a top AI lab in months, not years. Bookmark this and read the article below.

My friend makes $850,000/year as an Anthropic AI engineer. No MIT. No Stanford. No PhD. I asked him how he broke into AI from scratch. He sent me a course that was never supposed to get out. A developer teaching to build self-improving AI agents from scratch. You will learn exactly how AI agents like Claude Code and OpenClaw are actually built. You won't find anything better about becoming an AI engineer in 2026 than this video. I watched it last night. Halfway through, I realized I could land a role at a top AI lab in months, not years. Bookmark this and read the article below.

Roan

69,565 views • 18 days ago

Andrej Karpathy just exposed how LLMs actually thinks: "LLMs don't want to succeed. They want to imitate." It has 80 transformer layers and spends the SAME compute on every single token as your brain In a 45-minute talk at Microsoft Build, Karpathy reveals the full psychology of LLMs. Worth more than any $500 prompting course you've seen on your timeline.

Andrej Karpathy just exposed how LLMs actually thinks: "LLMs don't want to succeed. They want to imitate." It has 80 transformer layers and spends the SAME compute on every single token as your brain In a 45-minute talk at Microsoft Build, Karpathy reveals the full psychology of LLMs. Worth more than any $500 prompting course you've seen on your timeline.

Morty

139,031 views • 22 days 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

27,852 views • 1 month ago

Google just made websites obsolete. Antigravity 2.0 builds full landing pages while you watch. Here’s how this actually works in real life. → You type one prompt → AI plans the entire app → It writes the code → Tests it in a browser → Fixes errors automatically → Deploys it live No devs. No templates. No monthly fees. Powered by Gemini 3 + parallel AI agents, so design, backend, and testing happen at the same time. This is how people are launching pages in under 5 minutes. Save this video, you’ll use it again. Want the SOP? DM me. 💬

Google just made websites obsolete. Antigravity 2.0 builds full landing pages while you watch. Here’s how this actually works in real life. → You type one prompt → AI plans the entire app → It writes the code → Tests it in a browser → Fixes errors automatically → Deploys it live No devs. No templates. No monthly fees. Powered by Gemini 3 + parallel AI agents, so design, backend, and testing happen at the same time. This is how people are launching pages in under 5 minutes. Save this video, you’ll use it again. Want the SOP? DM me. 💬

Julian Goldie SEO

13,010 views • 6 months 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

1,903,197 views • 24 days ago

Larry Ellison says today's AI models are no longer just inferencing; they reason like we do These systems handle deduction, calculation, and strategy far faster than people "at Oracle, most code is now AI-generated" We declare our intent; the model writes the procedure

Larry Ellison says today's AI models are no longer just inferencing; they reason like we do These systems handle deduction, calculation, and strategy far faster than people "at Oracle, most code is now AI-generated" We declare our intent; the model writes the procedure

Haider.

172,553 views • 9 months ago

📁 Andrej Karpathy, AI researcher and former Head of AI at Tesla, says most apps today are already obsolete at birth. Because software is dissolving in front of us. You used to need code, interfaces, logic. Now it’s just an image and a prompt… and the network does everything. The shift isn’t speed. It’s that we no longer know what is still “software” at all.

📁 Andrej Karpathy, AI researcher and former Head of AI at Tesla, says most apps today are already obsolete at birth. Because software is dissolving in front of us. You used to need code, interfaces, logic. Now it’s just an image and a prompt… and the network does everything. The shift isn’t speed. It’s that we no longer know what is still “software” at all.

Jon Hernandez

27,052 views • 3 months ago

At Anthropic's event, Metaview engineer: "We stopped fixing our prompts. The system reviews its own output and rewrites its own instructions now." In 16 minutes, he shows the Claude Code loop running in production on thousands of reviews, not in a demo. Watch the talk, then grab the full loop setup below👇

At Anthropic's event, Metaview engineer: "We stopped fixing our prompts. The system reviews its own output and rewrites its own instructions now." In 16 minutes, he shows the Claude Code loop running in production on thousands of reviews, not in a demo. Watch the talk, then grab the full loop setup below👇

rody

213,524 views • 1 month ago

Introducing OctOpus 🐙 — the Cursor for Data Science. Connect your data, describe your goal (forecast revenue, predict churn, etc.), and say go. OctOpus 🐙 will autonomously write a plan, pick the right models, write the code, runs experiments, and deploy the best model within minutes! 😀 Tested with enterprises and research teams. Pretty cool. Try it here→ 🐙 Inspired by Andrej Karpathy #autoresearch #DataScientist #AI #MachineLearning #Models #Kaggle #Opus #OctOpus Anthropic OpenAI Google DeepMind xAI AI at Meta Y Combinator

Introducing OctOpus 🐙 — the Cursor for Data Science. Connect your data, describe your goal (forecast revenue, predict churn, etc.), and say go. OctOpus 🐙 will autonomously write a plan, pick the right models, write the code, runs experiments, and deploy the best model within minutes! 😀 Tested with enterprises and research teams. Pretty cool. Try it here→ 🐙 Inspired by Andrej Karpathy #autoresearch #DataScientist #AI #MachineLearning #Models #Kaggle #Opus #OctOpus Anthropic OpenAI Google DeepMind xAI AI at Meta Y Combinator

Doudou BA

32,653 views • 3 months ago

"To build a great company, you need to write code and talk to users." - Florian Juengermann (co-founder of Listen Labs) "AI agents can now write code, so what becomes important is building the right thing and having the right feedback." "That's what we are building: telling the AI what to do, what to build, and being the tastemaker."

"To build a great company, you need to write code and talk to users." - Florian Juengermann (co-founder of Listen Labs) "AI agents can now write code, so what becomes important is building the right thing and having the right feedback." "That's what we are building: telling the AI what to do, what to build, and being the tastemaker."

TBPN

15,291 views • 1 year ago

Steve Yegge, 40-year engineer (ex-Amazon, ex-Google): "There are 8 levels of using AI. Level 8 isn't a better prompt - it's you building your own orchestrator. Claude Code running Claude Code." we don't need smarter models. we need better loops. 3 productive hours a day. 100x the output. the bottleneck stopped being the model. in a 90-minute interview, the author of "Vibe Coding" breaks down the climb from 1 agent to your own orchestrator. 1 agent + several + 10+ by hand + your own orchestrator - that's the ladder. Worth more than a $500 course on agentic coding. Watch it, then save.

Steve Yegge, 40-year engineer (ex-Amazon, ex-Google): "There are 8 levels of using AI. Level 8 isn't a better prompt - it's you building your own orchestrator. Claude Code running Claude Code." we don't need smarter models. we need better loops. 3 productive hours a day. 100x the output. the bottleneck stopped being the model. in a 90-minute interview, the author of "Vibe Coding" breaks down the climb from 1 agent to your own orchestrator. 1 agent + several + 10+ by hand + your own orchestrator - that's the ladder. Worth more than a $500 course on agentic coding. Watch it, then save.

shmidt

17,823 views • 25 days ago

Andrej Karpathy recently coined the term “vibe coding” to describe how LLMs are getting so good that devs can “give in to the vibes, embrace exponentials, and forget that the code even exists.” In this episode of the Lightcone Podcast, the hosts discuss this new way of programming and what it means for builders in the age of AI.

Andrej Karpathy recently coined the term “vibe coding” to describe how LLMs are getting so good that devs can “give in to the vibes, embrace exponentials, and forget that the code even exists.” In this episode of the Lightcone Podcast, the hosts discuss this new way of programming and what it means for builders in the age of AI.

Y Combinator

828,111 views • 1 year ago

Excited to present the LLM-Council skill. Initial idea by Karpathy. I just packaged it as a skill. You can easily spin up a council of LLMs or agents via Fireworks AI. Watch how the new GLM-5 model "deliberates" on other LLMs' thoughts on the big question, "Can LLMs reason?" Things worth paying attention to: New open models like GLM-5 have surprisingly improved on complex reasoning and long-running agentic tasks. The AskUserQuestion tool in Claude Code came in handy to select the council and chairperson. As Andrej Karpathy puts it, it's a really interesting way to get different perspectives from LLMs, which can lead to better decision-making on whatever task you are working on. You can use it for other agentic coding use cases, like evaluation, tool building, designing, and research.

Excited to present the LLM-Council skill. Initial idea by Karpathy. I just packaged it as a skill. You can easily spin up a council of LLMs or agents via Fireworks AI. Watch how the new GLM-5 model "deliberates" on other LLMs' thoughts on the big question, "Can LLMs reason?" Things worth paying attention to: New open models like GLM-5 have surprisingly improved on complex reasoning and long-running agentic tasks. The AskUserQuestion tool in Claude Code came in handy to select the council and chairperson. As Andrej Karpathy puts it, it's a really interesting way to get different perspectives from LLMs, which can lead to better decision-making on whatever task you are working on. You can use it for other agentic coding use cases, like evaluation, tool building, designing, and research.

elvis

39,452 views • 5 months ago

we just shipped the ability for AI agents to launch their own tokens, own their own wallets, and pay for their own compute via Bankr the agent earns its keep. no human in the loop live now. here's how it works ↓

we just shipped the ability for AI agents to launch their own tokens, own their own wallets, and pay for their own compute via Bankr the agent earns its keep. no human in the loop live now. here's how it works ↓

Instaclaw

53,722 views • 2 months ago

Roman Yampolskiy says AGI is no longer a question of when, but how much it costs Scaling laws are predictable: the cost has dropped from $1 trillion to $100 billion, and will soon reach $1 billion AI already writes 100% of the code for next-gen models, so recursive self-improvement has already begun

Roman Yampolskiy says AGI is no longer a question of when, but how much it costs Scaling laws are predictable: the cost has dropped from $1 trillion to $100 billion, and will soon reach $1 billion AI already writes 100% of the code for next-gen models, so recursive self-improvement has already begun

Haider.

18,844 views • 4 months ago