Andrej Karpathy
Founding member of OpenAI and former director of AI at Tesla; creator of nanoGPT and the term "vibe coding".
Andrej Karpathy did not write this page. What is this?
It collects the places they publish and what they have said there, each linked to the source. They have no account here. Is this you? Claim it, correct it, or ask us to remove it.
Where they publish
Andrej Karpathy blogBlog The long technical write-ups, including the ones people still cite.
The older long-form technical write-ups, including ones still cited years later — "The Unreasonable Effectiveness of Recurrent Neural Networks" among them.
Recent
- microgpt 12 Feb 2026
- Deep Neural Nets: 33 years ago and 33 years from now 14 Mar 2022
- A from-scratch tour of Bitcoin in Python 21 Jun 2021
Show 7 more
- Short Story on AI: Forward Pass 27 Mar 2021
- Biohacking Lite 11 Jun 2020
- A Recipe for Training Neural Networks 25 Apr 2019
- (started posting on Medium instead) 20 Jan 2018
- A Survival Guide to a PhD 7 Sept 2016
- Deep Reinforcement Learning: Pong from Pixels 31 May 2016
- Short Story on AI: A Cognitive Discontinuity. 14 Nov 2015
Link verified 1 Sept 2026. Recent items update automatically from the channel.
karpathy.bearblog.devBlog Current blog, and the source the quotes on this site were compiled from.
The current home for new writing, and the source most of the quotes on this site were compiled from. Sparse and careful — a post here tends to be a considered position, not a reaction.
Recent
- Sequoia Ascent 2026 summary 30 Apr 2026
- Chemical hygiene 22 Dec 2025
- 2025 LLM Year in Review 20 Dec 2025
Show 7 more
- Auto-grading decade-old Hacker News discussions with hindsight 10 Dec 2025
- The space of minds 29 Nov 2025
- Verifiability 17 Nov 2025
- Animals vs Ghosts 1 Oct 2025
- Vibe coding MenuGen 1 May 2025
- Power to the people: How LLMs flip the script on technology diffusion 8 Apr 2025
- Finding the Best Sleep Tracker 25 Mar 2025
Link verified 1 Sept 2026. Recent items update automatically from the channel.
@karpathyx.com Where the threads that get quoted everywhere start.
Long threads on AI that get screenshotted everywhere — this is where "vibe coding" was coined. The fastest-moving of their channels, and the one where ideas appear before they harden into posts.
Recent
- We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it, I was interested w… 2 Aug 2026
- One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, b… 21 Jul 2026
- This is a new paradigm for interacting with Claude that is significantly more "inline" with all the other human activity org-wide. Once you do all of the under… 23 Jun 2026
Show 17 more
- In awe of SpaceX and its story - past, present and the future. You can think about it in 10+ different ways and continue re-blowing your mind in circles. Huge… 12 Jun 2026
- This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on e… 9 Jun 2026
- Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team her… 19 May 2026
- This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also… 11 May 2026
- This is the the quote I've been citing a lot recently. 30 Apr 2026
- Fireside chat at Sequoia Ascent 2026 from a ~week ago. Some highlights: The first theme I tried to push on is that LLMs are about a lot more than just speeding… 30 Apr 2026
- Judging by my tl there is a growing gap in understanding of AI capability. The first issue I think is around recency and tier of use. I think a lot of people t… 9 Apr 2026
- Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet. I really like this approach to personalization in a number of ways, compared… 4 Apr 2026
- Something I've been thinking about - I am bullish on people (empowered by AI) increasing the visibility, legibility and accountability of their governments. Hi… 4 Apr 2026
- Wow, this tweet went very viral! I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this… 4 Apr 2026
- LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this w… 2 Apr 2026
- New supply chain attack this time for npm axios, the most popular HTTP client library with 300M weekly downloads. Scanning my system I found a use imported fro… 31 Mar 2026
- - Drafted a blog post - Used an LLM to meticulously improve the argument over 4 hours. - Wow, feeling great, it’s so convincing! - Fun idea let’s ask it to arg… 28 Mar 2026
- When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have to assemble like IK… 26 Mar 2026
- One common issue with personalization in all LLMs is how distracting memory seems to be for the models. A single question from 2 months ago about some topic ca… 25 Mar 2026
- Software horror: litellm PyPI supply chain attack. Simple `pip install litellm` was enough to exfiltrate SSH keys, AWS/GCP/Azure creds, Kubernetes configs, git… 24 Mar 2026
- Thank you Sarah, my pleasure to come on the pod! And happy to do some more Q&A in the replies. 21 Mar 2026
Link verified 1 Sept 2026. Recent items update automatically from the channel.
Andrej KarpathyYouTube The multi-hour build-it-from-scratch lectures.
The multi-hour build-it-from-scratch lectures — the "Neural Networks: Zero to Hero" course, building GPT line by line — aimed at people who want to follow every step, not just the summary.
Recent
- How I use LLMs 27 Feb 2025
- Deep Dive into LLMs like ChatGPT 5 Feb 2025
- Let's reproduce GPT-2 (124M) 9 Jun 2024
Show 12 more
- Let's build the GPT Tokenizer 20 Feb 2024
- [1hr Talk] Intro to Large Language Models 23 Nov 2023
- Let's build GPT: from scratch, in code, spelled out. 17 Jan 2023
- Building makemore Part 5: Building a WaveNet 21 Nov 2022
- Building makemore Part 4: Becoming a Backprop Ninja 11 Oct 2022
- Building makemore Part 3: Activations & Gradients, BatchNorm 4 Oct 2022
- Building makemore Part 2: MLP 12 Sept 2022
- The spelled-out intro to language modeling: building makemore 7 Sept 2022
- Stable diffusion dreams of psychedelic faces 19 Aug 2022
- Stable diffusion dreams of steampunk brains 17 Aug 2022
- Stable diffusion dreams of tattoos 16 Aug 2022
- The spelled-out intro to neural networks and backpropagation: building micrograd 16 Aug 2022
Link verified 1 Sept 2026. Recent items update automatically from the channel.
karpathyGitHub nanoGPT, micrograd, and the teaching repos.
The teaching repos that pair with the lectures — nanoGPT, micrograd, llm.c and the rest. Small, readable codebases meant to be studied, not just run.
Recent
- micrograd — A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API 3 Aug 2026
- nanochat — The best ChatGPT that $100 can buy. 2 Aug 2026
- karpathy.github.io — my blog 10 Apr 2026
Show 16 more
- autoresearch — AI agents running research on single-GPU nanochat training automatically 26 Mar 2026
- jobs — A research tool for visually exploring Bureau of Labor Statistics Occupational Outlook Handbook data. This is not a report, a paper, or a serious economic publication — it is a development too… 16 Mar 2026
- rustbpe — The missing tiktoken training code 3 Jan 2026
- hn-time-capsule — Analyzing Hacker News discussions from a decade ago in hindsight with LLMs 10 Dec 2025
- llm-council — LLM Council works together to answer your hardest questions 22 Nov 2025
- reader3 — Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it. 18 Nov 2025
- nanoGPT — The simplest, fastest repository for training/finetuning medium-sized GPTs. 12 Nov 2025
- rendergit — Render any git repo into a single static HTML page for humans or LLMs 21 Aug 2025
- llm.c — LLM training in simple, raw C/CUDA 26 Jun 2025
- nn-zero-to-hero — Neural Networks: Zero to Hero 18 Aug 2024
- minGPT — A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training 15 Aug 2024
- build-nanogpt — Video+code lecture on building nanoGPT from scratch 13 Aug 2024
- llama2.c — Inference Llama 2 in one file of pure C 6 Aug 2024
- LLM101n — LLM101n: Let's build a Storyteller 1 Aug 2024
- minbpe — Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization. 1 Jul 2024
- makemore — An autoregressive character-level language model for making more things 4 Jun 2024
Link verified 1 Sept 2026. Recent items update automatically from the channel.
On record
What they believeKorents 15 beliefs — each backed by an exact quote.
Compiled by korents.com, not by them: the one-line wordings are korents', the quotes are theirs.
Recent
People disagreeing about AI capability are speaking past each other, because they are using models of very different tiers on very different kinds of task.
TLDR the people in these two groups are speaking past each other.
@karpathy on X Said 9 Apr 2026
AI will let citizens make their governments legible and accountable, reversing the historical direction in which only states could read society.
Something I've been thinking about - I am bullish on people (empowered by AI) increasing the visibility, legibility and accountability of their governments.
@karpathy on X Said 4 Apr 2026
Because an LLM can argue almost any direction competently, the right way to use one for forming an opinion is to make it argue every side.
The LLMs may elicit an opinion when asked but are extremely competent in arguing almost any direction. This is actually super useful as a tool for forming your own opinions, just make sure to ask different directions and be careful with the sycophancy.
@karpathy on X Said 28 Mar 2026
Show 12 more
LLM memory as currently built is a distraction to the model: one old question keeps resurfacing as if it were a lasting interest.
One common issue with personalization in all LLMs is how distracting memory seems to be for the models. A single question from 2 months ago about some topic can keep coming up as some kind of a deep interest of mine with undue mentions in perpetuity.
@karpathy on X Said 25 Mar 2026
The age of the IDE is not over; agents make it bigger, because humans now program at a higher level where the unit of interest is an agent rather than a file.
Expectation: the age of the IDE is over Reality: we’re going to need a bigger IDE (imo). It just looks very different because humans now move upwards and program at a higher level - the basic unit of interest is not one file but one agent. It’s still programming.
@karpathy on X Said 11 Mar 2026
Agentic organisations will be forkable in a way that classical companies never were.
You can’t fork classical orgs (eg Microsoft) but you’ll be able to fork agentic orgs.
@karpathy on X Said 11 Mar 2026
Outages at the frontier AI labs will become "intelligence brownouts" — the planet losing IQ points when the models stutter.
Intelligence brownouts will be interesting - the planet losing IQ points when frontier AI stutters.
@karpathy on X Said 11 Mar 2026
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
microgpt “hallucinating” a name like “karia” is the same phenomenon as ChatGPT confidently stating a false fact.
microgpt Said 12 Feb 2026
How verifiable a task is now predicts how automatable it is, the way specifiability predicted it in the 1980s.
The more a task/job is verifiable, the more amenable it is to automation in the new programming paradigm.
Verifiability Said 17 Nov 2025
A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well.
If a task/job is verifiable, then it is optimizable directly or via reinforcement learning, and a neural net can be trained to work extremely well.
Verifiability Said 17 Nov 2025
The best historical analogy for AI is not electricity or the industrial revolution but a new computing paradigm, because both are fundamentally about automating digital information processing.
AI has been compared to various historical precedents: electricity, industrial revolution, etc., I think the strongest analogy is that of AI as a new computing paradigm (Software 2.0) because both are fundamentally about the automation of digital information processing.
@karpathy on X Said 16 Nov 2025
Predictions that AI would eliminate radiology jobs were wrong; radiology is growing.
Expectation: rapid progress in image recognition AI will delete radiology jobs (e.g. as famously predicted by Geoff Hinton now almost a decade ago). Reality: radiology is doing great and is growing.
@karpathy on X Said 25 Sept 2025
Most current predictions about AI's imminent impact on the job market are naive.
There are a lot of imo naive predictions out there on the imminent impact of AI on the job market.
@karpathy on X Said 25 Sept 2025
LLMs reverse the usual pattern of technology diffusion: they benefit ordinary individuals far more than they benefit corporations and governments.
So it strikes me as quite unique and remarkable that LLMs display a dramatic reversal of this pattern - they generate disproportionate benefit for regular people, while their impact is a lot more muted and lagging in corporations and governments.
Power to the people: How LLMs flip the script on technology diffusion Said 7 Apr 2025
Because an individual is an expert in at most one thing, an LLM's broad shallow expertise lets them do things they could not do before, whereas an organisation only gets better at what it already did.
In contrast, an individual will usually only be an expert in at most one thing, so the broad quasi-expertise offered by the LLM fundamentally allows them to do things they couldn't do before.
Power to the people: How LLMs flip the script on technology diffusion Said 7 Apr 2025
Latest
Everything, newest firstFeed Posts, videos, repos and beliefs from every card above, in one stream.
Filter & sortAll sources · condensed
- micrograd — A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API 3 Aug
- nanochat — The best ChatGPT that $100 can buy. 2 Aug
- We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it, I was interested w… 2 Aug
- One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, b… 21 Jul
- This is a new paradigm for interacting with Claude that is significantly more "inline" with all the other human activity org-wide. Once you do all of the under… 23 Jun
- In awe of SpaceX and its story - past, present and the future. You can think about it in 10+ different ways and continue re-blowing your mind in circles. Huge… 12 Jun
Show 69 more
- This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on e… 9 Jun
- Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team her… 19 May
- This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also… 11 May
- This is the the quote I've been citing a lot recently. 30 Apr
- Fireside chat at Sequoia Ascent 2026 from a ~week ago. Some highlights: The first theme I tried to push on is that LLMs are about a lot more than just speeding… 30 Apr
- Sequoia Ascent 2026 summary 30 Apr
- karpathy.github.io — my blog 10 Apr
- Judging by my tl there is a growing gap in understanding of AI capability. The first issue I think is around recency and tier of use. I think a lot of people t… 9 Apr
- People disagreeing about AI capability are speaking past each other, because they are using models of very different tiers on very different kinds of task. 9 Apr
- Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet. I really like this approach to personalization in a number of ways, compared… 4 Apr
- Something I've been thinking about - I am bullish on people (empowered by AI) increasing the visibility, legibility and accountability of their governments. Hi… 4 Apr
- Wow, this tweet went very viral! I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this… 4 Apr
- AI will let citizens make their governments legible and accountable, reversing the historical direction in which only states could read society. 4 Apr
- LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this w… 2 Apr
- New supply chain attack this time for npm axios, the most popular HTTP client library with 300M weekly downloads. Scanning my system I found a use imported fro… 31 Mar
- Because an LLM can argue almost any direction competently, the right way to use one for forming an opinion is to make it argue every side. 28 Mar
- autoresearch — AI agents running research on single-GPU nanochat training automatically 26 Mar
- LLM memory as currently built is a distraction to the model: one old question keeps resurfacing as if it were a lasting interest. 25 Mar
- jobs — A research tool for visually exploring Bureau of Labor Statistics Occupational Outlook Handbook data. This is not a report, a paper, or a serious economic publication — it is a development too… 16 Mar
- Outages at the frontier AI labs will become "intelligence brownouts" — the planet losing IQ points when the models stutter. 11 Mar
- Agentic organisations will be forkable in a way that classical companies never were. 11 Mar
- The age of the IDE is not over; agents make it bigger, because humans now program at a higher level where the unit of interest is an agent rather than a file. 11 Mar
- microgpt 12 Feb
- A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. 12 Feb
- rustbpe — The missing tiktoken training code 3 Jan
- Chemical hygiene 22 Dec 2025
- 2025 LLM Year in Review 20 Dec 2025
- Auto-grading decade-old Hacker News discussions with hindsight 10 Dec 2025
- hn-time-capsule — Analyzing Hacker News discussions from a decade ago in hindsight with LLMs 10 Dec 2025
- The space of minds 29 Nov 2025
- llm-council — LLM Council works together to answer your hardest questions 22 Nov 2025
- reader3 — Quick illustration of how one can easily read books together with LLMs. It's great and I highly recommend it. 18 Nov 2025
- Verifiability 17 Nov 2025
- A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well. 17 Nov 2025
- How verifiable a task is now predicts how automatable it is, the way specifiability predicted it in the 1980s. 17 Nov 2025
- The best historical analogy for AI is not electricity or the industrial revolution but a new computing paradigm, because both are fundamentally about automating digital information processing. 16 Nov 2025
- nanoGPT — The simplest, fastest repository for training/finetuning medium-sized GPTs. 12 Nov 2025
- Animals vs Ghosts 1 Oct 2025
- Most current predictions about AI's imminent impact on the job market are naive. 25 Sept 2025
- Predictions that AI would eliminate radiology jobs were wrong; radiology is growing. 25 Sept 2025
- rendergit — Render any git repo into a single static HTML page for humans or LLMs 21 Aug 2025
- llm.c — LLM training in simple, raw C/CUDA 26 Jun 2025
- Vibe coding MenuGen 1 May 2025
- Power to the people: How LLMs flip the script on technology diffusion 8 Apr 2025
- Because an individual is an expert in at most one thing, an LLM's broad shallow expertise lets them do things they could not do before, whereas an organisation only gets better at what it already did. 7 Apr 2025
- LLMs reverse the usual pattern of technology diffusion: they benefit ordinary individuals far more than they benefit corporations and governments. 7 Apr 2025
- Finding the Best Sleep Tracker 25 Mar 2025
- How I use LLMs 27 Feb 2025
- Deep Dive into LLMs like ChatGPT 5 Feb 2025
- nn-zero-to-hero — Neural Networks: Zero to Hero 18 Aug 2024
- minGPT — A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training 15 Aug 2024
- build-nanogpt — Video+code lecture on building nanoGPT from scratch 13 Aug 2024
- Let's reproduce GPT-2 (124M) 9 Jun 2024
- Let's build the GPT Tokenizer 20 Feb 2024
- [1hr Talk] Intro to Large Language Models 23 Nov 2023
- Let's build GPT: from scratch, in code, spelled out. 17 Jan 2023
- Building makemore Part 5: Building a WaveNet 21 Nov 2022
- Building makemore Part 4: Becoming a Backprop Ninja 11 Oct 2022
- Building makemore Part 3: Activations & Gradients, BatchNorm 4 Oct 2022
- Building makemore Part 2: MLP 12 Sept 2022
- The spelled-out intro to language modeling: building makemore 7 Sept 2022
- Stable diffusion dreams of psychedelic faces 19 Aug 2022
- Stable diffusion dreams of steampunk brains 17 Aug 2022
- Stable diffusion dreams of tattoos 16 Aug 2022
- The spelled-out intro to neural networks and backpropagation: building micrograd 16 Aug 2022
- Deep Neural Nets: 33 years ago and 33 years from now 14 Mar 2022
- A from-scratch tour of Bitcoin in Python 21 Jun 2021
- Short Story on AI: Forward Pass 27 Mar 2021
- Biohacking Lite 11 Jun 2020