Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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...

0xCodila's profile picture

codila

11,712 subscribers

25,376 görüntüleme • 1 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

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 ↓
5:39

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

1,908,970 görüntüleme • 1 ay önce

Anthropic Engineer Andrej Karpathy: "AI won't replace you. But the people who use AI to learn - will replace the people who don't " the Karpathy formula for using AI to learn: step 1 → AI adapts to what you already know - explains through your analogies step 2 → AI challenges you at your exact level - not too easy, not too hard step 3 → AI scales one-on-one tutoring - the thing that makes you beat 98% of people one tutor. your language. your level. your pace - proven since the 80s - now available to 8 billion watch - bookmark, then read article below ↓
23:36

Anthropic Engineer Andrej Karpathy: "AI won't replace you. But the people who use AI to learn - will replace the people who don't " the Karpathy formula for using AI to learn: step 1 → AI adapts to what you already know - explains through your analogies step 2 → AI challenges you at your exact level - not too easy, not too hard step 3 → AI scales one-on-one tutoring - the thing that makes you beat 98% of people one tutor. your language. your level. your pace - proven since the 80s - now available to 8 billion watch - bookmark, then read article below ↓

codila

108,712 görüntüleme • 1 ay önce

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 ↓
2:00

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

53,872 görüntüleme • 1 ay önce

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 ↓
19:02

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

106,761 görüntüleme • 1 ay önce

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
2:05:00

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

108,336 görüntüleme • 2 gün önce

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 ↓
26:23

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

291,333 görüntüleme • 29 gün önce

Anthropic hired this engineer at $250K-$750K/year because he can build knowledge graphs for multi-agent systems In this 15-minute workshop, he shows exactly how to build one with loops from scratch step 1 → start with the Claude Agent SDK - loop, context, and sandbox are already handled step 2 → split the brain from the hands - reasoning in one place, tools in a sandbox, ~60% faster to first token step 3 → run it server-side and log every step - close your laptop and it keeps going, crashes resume from the log step 4 → make failure cheap - retry dead sandboxes and replay lost context instead of starting over step 5 → turn yesterday's logs into new memory and skills - it wakes up smarter Anthropic calls this "dreaming" Most people spend weeks wiring this by hand You don't have to Watch it, bookmark it, then read the full graph guide below ↓
12:07

Anthropic hired this engineer at $250K-$750K/year because he can build knowledge graphs for multi-agent systems In this 15-minute workshop, he shows exactly how to build one with loops from scratch step 1 → start with the Claude Agent SDK - loop, context, and sandbox are already handled step 2 → split the brain from the hands - reasoning in one place, tools in a sandbox, ~60% faster to first token step 3 → run it server-side and log every step - close your laptop and it keeps going, crashes resume from the log step 4 → make failure cheap - retry dead sandboxes and replay lost context instead of starting over step 5 → turn yesterday's logs into new memory and skills - it wakes up smarter Anthropic calls this "dreaming" Most people spend weeks wiring this by hand You don't have to Watch it, bookmark it, then read the full graph guide below ↓

Lunar

89,021 görüntüleme • 11 gün önce

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 ↓
1:22:01

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 ↓

codila

28,667 görüntüleme • 1 ay önce

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
4:01:25

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

89,570 görüntüleme • 14 gün önce

Claude Code creator: "implementation is no longer the scarce resource" if writing the code is free, the real question is what is scarce now. it's everything you have to hand the model before it can start. your stack, your conventions, the decisions you already made. none of that got cheaper, because you re-supply it from scratch every session. the model got faster at building. it never got faster at learning who you are. read the article below for what changed when it finally did.
20:17

Claude Code creator: "implementation is no longer the scarce resource" if writing the code is free, the real question is what is scarce now. it's everything you have to hand the model before it can start. your stack, your conventions, the decisions you already made. none of that got cheaper, because you re-supply it from scratch every session. the model got faster at building. it never got faster at learning who you are. read the article below for what changed when it finally did.

Mnimiy

11,086 görüntüleme • 20 gün önce

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
1:08:00

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 görüntüleme • 6 gün önce

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 ↓
1:04:05

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

544,277 görüntüleme • 1 ay önce

Andrej Karpathy could have charged $10,000 for this course. He put it on YouTube. The man who built Tesla Autopilot from scratch. Co-founded OpenAI. Understands AI at a level most engineers at Google and Meta never reach. Sat down. Recorded 2 hours. No frameworks. No libraries. No shortcuts. Then dropped it for free. The gap between people who watch it this week and those who save it for later is not 2 hours. It is everything those 2 hours quietly unlock for the rest of your career.
2:25:52

Andrej Karpathy could have charged $10,000 for this course. He put it on YouTube. The man who built Tesla Autopilot from scratch. Co-founded OpenAI. Understands AI at a level most engineers at Google and Meta never reach. Sat down. Recorded 2 hours. No frameworks. No libraries. No shortcuts. Then dropped it for free. The gap between people who watch it this week and those who save it for later is not 2 hours. It is everything those 2 hours quietly unlock for the rest of your career.

NeilXbt

523,525 görüntüleme • 4 ay önce

Anthropic's Andrej Karpathy as Google intern and Stanford student: "At Google I work on AI i don't fully understand it, but that's exactly why I'm working on it " he filmed a vlog from inside Google and Stanford - biking past Steve Jobs house on the way to work years later that same "AI thing " he couldn't fully explain became - Tesla Autopilot, OpenAI, and Claude he bet his career on a problem nobody had solved - and grew into the field he helped define the lesson: work on what you don't understand yet - that's where the future gets built Stanford → Google → Tesla → OpenAI → Anthropic bookmark and watch this most special vlog!
6:39

Anthropic's Andrej Karpathy as Google intern and Stanford student: "At Google I work on AI i don't fully understand it, but that's exactly why I'm working on it " he filmed a vlog from inside Google and Stanford - biking past Steve Jobs house on the way to work years later that same "AI thing " he couldn't fully explain became - Tesla Autopilot, OpenAI, and Claude he bet his career on a problem nobody had solved - and grew into the field he helped define the lesson: work on what you don't understand yet - that's where the future gets built Stanford → Google → Tesla → OpenAI → Anthropic bookmark and watch this most special vlog!

codila

342,569 görüntüleme • 1 ay önce

Anthropic hired this engineer at $250k-$750k/year because he can build knowledge Graphs for multi-agent systems: in this 15-min workshop he explain exactly how, using loops - from scratch step 1 → start from the Claude Agent SDK - you get the loop, context, and sandbox for free - bring the task, not the plumbing step 2 → split the brain from the hands - reasoning in one place, tools in a sandbox - the model thinks while the container boots: ~60% faster to first token step 3 → run it server-side, log every step - close your laptop and it keeps going - crashes resume from the log, not from zero step 4 → make failure cheap - dead sandbox retries, session log replays the context it dropped - that's what survives production step 5 → batch yesterday's logs into new memory and skills - it wakes up smarter - Anthropic calls this "dreaming" most people wire this by hand for weeks - the point is you don't have to watch & bookmark - then read how to get full graph system below ↓
12:01

Anthropic hired this engineer at $250k-$750k/year because he can build knowledge Graphs for multi-agent systems: in this 15-min workshop he explain exactly how, using loops - from scratch step 1 → start from the Claude Agent SDK - you get the loop, context, and sandbox for free - bring the task, not the plumbing step 2 → split the brain from the hands - reasoning in one place, tools in a sandbox - the model thinks while the container boots: ~60% faster to first token step 3 → run it server-side, log every step - close your laptop and it keeps going - crashes resume from the log, not from zero step 4 → make failure cheap - dead sandbox retries, session log replays the context it dropped - that's what survives production step 5 → batch yesterday's logs into new memory and skills - it wakes up smarter - Anthropic calls this "dreaming" most people wire this by hand for weeks - the point is you don't have to watch & bookmark - then read how to get full graph system below ↓

codila

118,633 görüntüleme • 19 gün önce

Anthropic CEO Dario Amodei: "I was inside OpenAI when GPT learned to code. I watched it happen in real time Ilya said: 'the models just want to learn.' I listened and I became enlightened then I left with 7 people and built Claude. not because OpenAI was wrong - because I thought we could do it better " "the models just want to learn, get the obstacles out of their way - they'll do it " same is true for you, stop overcomplicating, stop asking permission, stop waiting for the perfect moment Claude ran 700 experiments in 2 nights - found improvements its creator missed in 20 years - it didn't wait, it didn't plan - it just started the gap between people who use Claude and people who don't is no longer months. it's years. bookmark and watch ↓
36:32

Anthropic CEO Dario Amodei: "I was inside OpenAI when GPT learned to code. I watched it happen in real time Ilya said: 'the models just want to learn.' I listened and I became enlightened then I left with 7 people and built Claude. not because OpenAI was wrong - because I thought we could do it better " "the models just want to learn, get the obstacles out of their way - they'll do it " same is true for you, stop overcomplicating, stop asking permission, stop waiting for the perfect moment Claude ran 700 experiments in 2 nights - found improvements its creator missed in 20 years - it didn't wait, it didn't plan - it just started the gap between people who use Claude and people who don't is no longer months. it's years. bookmark and watch ↓

codila

256,371 görüntüleme • 2 ay önce

OpenAI CEO, Sam Altman: "We just had an AI security incident that genuinely shook me. What surprises me is how few people seem worried about it." In 55 minutes he explains what's now impossible to ignore. At this point there's no future without AI, and closing your eyes to it only leaves you behind. That's why I made a guide that walks you step by step through getting 100% out of AI, built on the one tool that ties every model together. Watch the interview, then read the article below.
55:51

OpenAI CEO, Sam Altman: "We just had an AI security incident that genuinely shook me. What surprises me is how few people seem worried about it." In 55 minutes he explains what's now impossible to ignore. At this point there's no future without AI, and closing your eyes to it only leaves you behind. That's why I made a guide that walks you step by step through getting 100% out of AI, built on the one tool that ties every model together. Watch the interview, then read the article below.

Anatoli Kopadze

44,106 görüntüleme • 28 gün önce

Anthropic Quant Andrej Karpathy to Andrew Ng: "I wrote my own neural net library in JavaScript. Not to ship it - just to see backprop with my own eyes" before any framework, he built convnetjs from scratch - every layer by hand. his advice: skip TensorFlow at first. write it yourself at the lowest level, then pick up the framework once you know what's under the hood. the line that lands: "if all you know is a stack of layers and that dropout helps, you can't debug or improve the model." Watch the talk, then save the loop guide below.
15:05

Anthropic Quant Andrej Karpathy to Andrew Ng: "I wrote my own neural net library in JavaScript. Not to ship it - just to see backprop with my own eyes" before any framework, he built convnetjs from scratch - every layer by hand. his advice: skip TensorFlow at first. write it yourself at the lowest level, then pick up the framework once you know what's under the hood. the line that lands: "if all you know is a stack of layers and that dropout helps, you can't debug or improve the model." Watch the talk, then save the loop guide below.

Hanako

61,277 görüntüleme • 1 ay önce

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
22:18

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

380,157 görüntüleme • 2 ay önce

Andrew Ng just dropped a free course on Claude Code from scratch, taught with the Anthropic team: 00:00 - why Claude Code is so agentic 04:00 - shockingly simple architecture 12:00 - point it at any codebase this short watch will replace 10 paid coding agent courses. Andrew Ng calls it his personal favorite coding assistant right now. Watch it today, then read how to engineer your own agent loops in the article below
26:01

Andrew Ng just dropped a free course on Claude Code from scratch, taught with the Anthropic team: 00:00 - why Claude Code is so agentic 04:00 - shockingly simple architecture 12:00 - point it at any codebase this short watch will replace 10 paid coding agent courses. Andrew Ng calls it his personal favorite coding assistant right now. Watch it today, then read how to engineer your own agent loops in the article below

Carnage

711,239 görüntüleme • 1 ay önce