Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Andrej Karpathy just reveales how LLMs actually thinks: "GPT-4 knows it failed. It just won't tell you unless you ask." >80% of GPT-4 errors are recoverable - the model already knows it screwed up. It has 80 transformer layers and spends the SAME compute on every single token as... show more

Ricker

8,191 subscribers

163,114 Aufrufe • vor 1 Monat •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

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

140,240 Aufrufe • vor 1 Monat

Anthropic Engineer Andrej Karpathy just said what no one wants to admit: "Agents aren't magic. They're distillation at scale." Your agent loop is generating garbage at scale and you can't see it." LLMs are wasting 99.99% of their capacity on useless data. In a 20-minute conversation, Karpathy reveals the full reasoning stack Worth more than any $500 AI course you've seen this year.

Anthropic Engineer Andrej Karpathy just said what no one wants to admit: "Agents aren't magic. They're distillation at scale." Your agent loop is generating garbage at scale and you can't see it." LLMs are wasting 99.99% of their capacity on useless data. In a 20-minute conversation, Karpathy reveals the full reasoning stack Worth more than any $500 AI course you've seen this year.

Morty

95,477 Aufrufe • vor 3 Tagen

Andrej Karpathy in Stanford classroom said: "GPT is not a language model - It's a general-purpose computer" 90% of AI Twitter still thinks it's just autocomplete. It's not. >90% of the tools built on top of LLMs treat them like a smarter search engine. In this 40-minute lecture, Karpathy builds nanoGPT live 300 lines, reproduces GPT-2, explains every single decision. Worth more than any $500 deep learning bootcamp.

Andrej Karpathy in Stanford classroom said: "GPT is not a language model - It's a general-purpose computer" 90% of AI Twitter still thinks it's just autocomplete. It's not. >90% of the tools built on top of LLMs treat them like a smarter search engine. In this 40-minute lecture, Karpathy builds nanoGPT live 300 lines, reproduces GPT-2, explains every single decision. Worth more than any $500 deep learning bootcamp.

Ricker

117,471 Aufrufe • vor 1 Monat

Andrej Karpathy just broke the entire premise of modern AI: "Agents aren't magic. They're distillation at scale." 99.99% of your LLM's capacity is wasted on garbage data it never needed. Small model + right tools + closed loop = terrifying capability. In a 16-minute conversation, Karpathy reveals the full reasoning stack. Worth more than any $500 AI course you've seen this year.

Andrej Karpathy just broke the entire premise of modern AI: "Agents aren't magic. They're distillation at scale." 99.99% of your LLM's capacity is wasted on garbage data it never needed. Small model + right tools + closed loop = terrifying capability. In a 16-minute conversation, Karpathy reveals the full reasoning stack. Worth more than any $500 AI course you've seen this year.

Morty

673,033 Aufrufe • vor 1 Monat

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. 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. 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

39,593 Aufrufe • vor 6 Monaten

A lot of people shat on GPT-5 when it came out All of those people are wrong. GPT-5 is actually insanely good. It just requires a different style of prompting than any other model If you prompt it correctly, it's the best AI model out there Here's exactly how to do that:

A lot of people shat on GPT-5 when it came out All of those people are wrong. GPT-5 is actually insanely good. It just requires a different style of prompting than any other model If you prompt it correctly, it's the best AI model out there Here's exactly how to do that:

Alex Finn

19,286 Aufrufe • vor 1 Jahr

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

312,765 Aufrufe • vor 1 Monat

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people are still treating LLMs like chatbots. Karpathy is showing the full stack: Memory → Vision → Reasoning → Search → Tools Prompting is the old workflow. Agentic systems are the new one. This 40-minute talk is worth more than most paid AI agent courses. Bookmark and watch it before everyone catches up. Then read how to turn LLMs into self-improving agent loops below

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people are still treating LLMs like chatbots. Karpathy is showing the full stack: Memory → Vision → Reasoning → Search → Tools Prompting is the old workflow. Agentic systems are the new one. This 40-minute talk is worth more than most paid AI agent courses. Bookmark and watch it before everyone catches up. Then read how to turn LLMs into self-improving agent loops below

Lunar

354,047 Aufrufe • vor 28 Tagen

Andrej Karpathy spent 70 minutes breaking down how top AI users actually work with LLMs. The reality is simpler than people expect. You tell the model what you want in plain language and let it run. No 40-line system prompts. No secret tricks. By 2026 the engineer who writes off LLMs loses to the junior who just set one up properly. 70 minutes. Free. A rare straight look from an OpenAI co-founder. Bookmark it and watch.

Andrej Karpathy spent 70 minutes breaking down how top AI users actually work with LLMs. The reality is simpler than people expect. You tell the model what you want in plain language and let it run. No 40-line system prompts. No secret tricks. By 2026 the engineer who writes off LLMs loses to the junior who just set one up properly. 70 minutes. Free. A rare straight look from an OpenAI co-founder. Bookmark it and watch.

Andrew

351,387 Aufrufe • vor 2 Monaten

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 this 15-min talk, Karpathy breaks down how AI models actually works.

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 this 15-min talk, Karpathy breaks down how AI models actually works.

Ricker

11,402 Aufrufe • vor 1 Monat

Prime Intellect engineer: "everyone's bragging about a million-token context. here's what they don't tell you. at 256k tokens GPT-5.5 scores 80% on retrieval. push it to a million and it drops to 36%. the model accepts the context, it just can't reason across it. people call it context rot." in a 20-minute talk he explains why bigger context windows won't save your agents. continual learning + training on your own traces + real environments - that's the fix. Watch the talk, then save!

Prime Intellect engineer: "everyone's bragging about a million-token context. here's what they don't tell you. at 256k tokens GPT-5.5 scores 80% on retrieval. push it to a million and it drops to 36%. the model accepts the context, it just can't reason across it. people call it context rot." in a 20-minute talk he explains why bigger context windows won't save your agents. continual learning + training on your own traces + real environments - that's the fix. Watch the talk, then save!

Carnage

748,728 Aufrufe • vor 1 Monat

Andrej Karpathy: "Prompting is fading away. Delete everything else and keep the graph." in 68 minutes at Stanford he explains how to build one and why it is the layer everything ends up becoming LLMs → Prompts → Agents → Graphs everything before the graph is a step the graph is where the system stops being steps most people are still perfecting the thing that goes away first same model, same tokens, and the only thing that changes is the shape you run it in watch it today, then save the full graph engineering guide below

Andrej Karpathy: "Prompting is fading away. Delete everything else and keep the graph." in 68 minutes at Stanford he explains how to build one and why it is the layer everything ends up becoming LLMs → Prompts → Agents → Graphs everything before the graph is a step the graph is where the system stops being steps most people are still perfecting the thing that goes away first same model, same tokens, and the only thing that changes is the shape you run it in watch it today, then save the full graph engineering guide below

Hanako

127,756 Aufrufe • vor 8 Tagen

Andrej Karpathy spent 8 years at OpenAI & Tesla, recently he joined Anthropic Few days ago, he put everything he knows into one free 4-hour lecture After this course you'll learn to build LLMs like ChatGPT & Claude from scratch People pay $15k for bootcamps that teach half of this You probably don't have 4 hours right now Don't let this get lost in your feed Watch it, then read the guide below and build your first loop

Andrej Karpathy spent 8 years at OpenAI & Tesla, recently he joined Anthropic Few days ago, he put everything he knows into one free 4-hour lecture After this course you'll learn to build LLMs like ChatGPT & Claude from scratch People pay $15k for bootcamps that teach half of this You probably don't have 4 hours right now Don't let this get lost in your feed Watch it, then read the guide below and build your first loop

Roan

90,829 Aufrufe • vor 16 Tagen

Andrej Karpathy spent 8 years working at OpenAI and Tesla Last week, he condensed everything he knows into one free 2-hour lecture People spend $15K on bootcamps that teach less than half of this You probably don't have two hours to watch it right now Just don't let it disappear in your feed Save it, watch it later, then read the guide below and build your first loop

Andrej Karpathy spent 8 years working at OpenAI and Tesla Last week, he condensed everything he knows into one free 2-hour lecture People spend $15K on bootcamps that teach less than half of this You probably don't have two hours to watch it right now Just don't let it disappear in your feed Save it, watch it later, then read the guide below and build your first loop

Lunar

116,560 Aufrufe • vor 4 Tagen

Andrej Karpathy just built GPT-2 from scratch on camera! Every line. Every component. Every optimization decision. Transformer blocks. Self-attention. MLP. Mixed precision. Flash Attention. AdamW. Distributed training across GPUs. 4 hours. Free. Not a lecture about how GPT-2 was built. The actual build. Running. Training. Evaluated against the original OpenAI checkpoints. The engineers who watch this do not just understand language models. They understand them at the level required to build the next one. The gap between using AI and being capable of building it is not a PhD program. It is 4 hours with the person who makes this look like something any determined engineer can do.

Andrej Karpathy just built GPT-2 from scratch on camera! Every line. Every component. Every optimization decision. Transformer blocks. Self-attention. MLP. Mixed precision. Flash Attention. AdamW. Distributed training across GPUs. 4 hours. Free. Not a lecture about how GPT-2 was built. The actual build. Running. Training. Evaluated against the original OpenAI checkpoints. The engineers who watch this do not just understand language models. They understand them at the level required to build the next one. The gap between using AI and being capable of building it is not a PhD program. It is 4 hours with the person who makes this look like something any determined engineer can do.

NeilXbt

37,778 Aufrufe • vor 4 Monaten

Andrej Karpathy: "The future is not writing code. The future is writing the loops that write the code. The leverage point has moved one floor up." This is the shift that defines the next era of coding and quant building. 1 hour of pure insight on agentic AI coding and loop engineering from the OpenAI co-founder who just joined Anthropic to build self improving Claude. Worth more than every $500 vibe coding course combined. Watch it, then read the full guide on how to build your first self improving quant trading loop below.

Andrej Karpathy: "The future is not writing code. The future is writing the loops that write the code. The leverage point has moved one floor up." This is the shift that defines the next era of coding and quant building. 1 hour of pure insight on agentic AI coding and loop engineering from the OpenAI co-founder who just joined Anthropic to build self improving Claude. Worth more than every $500 vibe coding course combined. Watch it, then read the full guide on how to build your first self improving quant trading loop below.

Roan

37,862 Aufrufe • vor 2 Monaten

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

1,204,298 Aufrufe • vor 3 Monaten

This has been possible for months and barely anyone is doing it Months ago, Andrej Karpathy, a co-founder of OpenAI, open-sourced a project that gets you the best possible answers instead of trusting one model on its own. It's called LLM Council. Repo: /karpathy/llm-council The idea in two lines: your question goes to several models at once, Claude, GPT, Gemini, whatever you pick. They answer independently, then anonymously critique and rank each other (anonymous so they can't play favorites), and a chairman model merges the best of all of it into one final answer. One model just agrees with you; a council catches each other's mistakes. How to set it up: > Clone the repo > It uses uv for setup, install dependencies with uv sync > Get an OpenRouter API key and add it, this is what lets one app reach Claude, GPT, and Gemini together > Pick which models sit on your council in the config, then run it. It opens as a local web app, like ChatGPT but with a whole panel answering Bookmark this

This has been possible for months and barely anyone is doing it Months ago, Andrej Karpathy, a co-founder of OpenAI, open-sourced a project that gets you the best possible answers instead of trusting one model on its own. It's called LLM Council. Repo: /karpathy/llm-council The idea in two lines: your question goes to several models at once, Claude, GPT, Gemini, whatever you pick. They answer independently, then anonymously critique and rank each other (anonymous so they can't play favorites), and a chairman model merges the best of all of it into one final answer. One model just agrees with you; a council catches each other's mistakes. How to set it up: > Clone the repo > It uses uv for setup, install dependencies with uv sync > Get an OpenRouter API key and add it, this is what lets one app reach Claude, GPT, and Gemini together > Pick which models sit on your council in the config, then run it. It opens as a local web app, like ChatGPT but with a whole panel answering Bookmark this

Yarchi

21,488 Aufrufe • vor 2 Monaten

Open-source LLMs are getting really good. They’re not as powerful as GPT-4, but they’re improving quickly and worth experimenting with. If you want to run AI models like Mistral-7B on your laptop this is the easiest way to do it.

Open-source LLMs are getting really good. They’re not as powerful as GPT-4, but they’re improving quickly and worth experimenting with. If you want to run AI models like Mistral-7B on your laptop this is the easiest way to do it.

Mckay Wrigley

575,635 Aufrufe • vor 2 Jahren

KARPATHY WAS RIGHT. THIS 40-MINUTE Y COMBINATOR LECTURE PROVES IT Karpathy said we're in the 1960s of AI - most people using Claude Opus 4.8 are still acting like it's just a search engine > software 3.0 - LLMs as operating systems, not chatbots > autonomous agents that run entire workflows without you watching the 32 skills in this article are how you actually cross that line bookmark this 👇

KARPATHY WAS RIGHT. THIS 40-MINUTE Y COMBINATOR LECTURE PROVES IT Karpathy said we're in the 1960s of AI - most people using Claude Opus 4.8 are still acting like it's just a search engine > software 3.0 - LLMs as operating systems, not chatbots > autonomous agents that run entire workflows without you watching the 32 skills in this article are how you actually cross that line bookmark this 👇

Mr. Buzzoni

567,638 Aufrufe • vor 3 Monaten