Top all-time · #1828
Andrej Karpathy
Personal blog · karpathy.bearblog.devaiprogramming
Andrej Karpathy writes karpathy, a personal blog at karpathy.bearblog.dev about ai and programming. Since 2025, 42 different Hacker News readers have linked it 51 times, most often “The append-and-review note”. It is still writing: the last post was on 2026-10-31, and you can follow it by feed.
Bear blog of Andrej Karpathy, AI researcher. Started March 2025. main webpage: karpathy.ai 𝕏 @karpathy Subscribe to this blog via RSS feed ...
Most-linked posts?
- The append-and-review note7 people · 8 mentions · first linked 2025-03-19
- Auto-grading decade-old Hacker News discussions with hindsight7 people · 7 mentions · first linked 2025-12-10
- Finding the Best Sleep Tracker6 people · 6 mentions · first linked 2025-03-25
- Chemical Hygiene5 people · 5 mentions · first linked 2025-12-19
- LLMs flip the script on technology diffusion4 people · 4 mentions · first linked 2025-04-07
- Vibe Coding MenuGen4 people · 4 mentions · first linked 2025-05-01
- LLM Year in Review3 people · 3 mentions · first linked 2025-12-19
- Digital Hygiene3 people · 3 mentions · first linked 2025-03-18
- Karpathy: LLMs are "ghosts," not "animals"2 people · 2 mentions · first linked 2025-10-02
- The space of minds2 people · 2 mentions · first linked 2025-11-30
What Hacker News says?
Thank you. It was a great one-shot and I didn't end up doing any updates. Thrilled to see how it inspired work from: Thomas Morford (CSE @ UC Merced, thomasm6m6) who did the amazing article/thread generation (in < 100 lines of PY!): https://sw.vtom.net/hn35/news.html ; and also from Andrej Karpathy (ex-OpenAI, now Eureak Labs, karpathy) who did an interesting analysis of prescience quality of threads/commenters insp…
Comment linking /auto-grade-hn/
on “Show HN: Gemini Pro 3 imagines the HN front page 10 years from now”Submitted HackerTube: YouTube built from videos recommended by HN as a story · 2290 points
HN discussionWhat is this "clerk" library he used at this timestamp to tell him what to do? https://youtu.be/LCEmiRjPEtQ?si=XaC-oOMUxXp0DRU0&t=1991 Gemini found it via screenshot or context: https://clerk.com/ This is what he used for login on MenuGen: https://karpathy.bearblog.dev/vibe-coding-menugen/
Comment linking /vibe-coding-menugen/
on “Andrej Karpathy: Software in the era of AI [video]”Submitted Auto-grading decade-old Hacker News discussions with hindsight as a story · 686 points
HN discussionThe essence of it is that after the "read the whole internet and predict the next token" pre-training step (and the chat fine-tuning), SotA LLMs now have a training step where they solve huge numbers of tasks that have verifiable answers (especially programming and math). The model therefore gets the very broad general knowledge and natural language abilities from pre-training and gets good at solving actual problem…
Comment linking /year-in-review-2025/
on “The Illustrated Transformer”Submitted LLM Year in Review as a story · 377 points
HN discussionHere's the source for the jagged spiky intelligence diagram: https://x.com/colin_fraser/status/1994235521812328695 https://karpathy.bearblog.dev/the-space-of-minds/
Comment linking /the-space-of-minds/
on “LLM Year in Review”Submitted The space of minds as a story · 93 points
HN discussionHe has a new blog at https://karpathy.bearblog.dev/blog/
Comment linking /blog/
on “Backpropagation is a leaky abstraction (2016)”Submitted The append-and-review note as a story · 91 points
HN discussionI did that and see karpathy has a bearblog https://karpathy.bearblog.dev/ wow ref: https://news.ycombinator.com/item?id=46095250
Comment linking /
on “Tell HN: Want a better HN? Visit /newest”Submitted Finding the Best Sleep Tracker as a story · 61 points
HN discussionThis caused me to delete the HN password on my main account. It was already disconcerting to be reminded by Karpathy (I cannot help but see this as bragging) in his recent post that we must be good because LLMs are watching: https://karpathy.bearblog.dev/auto-grade-hn/ LLMs will be used to deanonymize all internet users. The AI "visionaries" are already bragging about this. You have been warned.
Comment linking /auto-grade-hn/
on “Show HN: HN Wrapped 2025 - an LLM reviews your year on HN”Submitted Digital Hygiene as a story · 39 points
HN discussionKarpathy himself has used "vibe coding" to describe "usage of LLMs for coding," so it's fair to say the definition has expanded. https://karpathy.bearblog.dev/year-in-review-2025/
Comment linking /year-in-review-2025/
on “Reflections on AI at the End of 2025”Submitted Digital Hygiene as a story · 31 points
HN discussionI like "ghosts" as a simple metaphor for what you chat with when you chat with AI. Usually we chat with Casper the Friendly Ghost, but there are a lot of other ghosts that can be conjured up. Some people are obsessed with chatting with ghosts. It seems like a rational adult couldn't be seriously harmed by chatting with a ghost, but there are news reports showing that some people get possessed. It's a better metaphor…
Comment linking /animals-vs-ghosts/
on “AI capability isn't humanness”Submitted LLMs flip the script on technology diffusion as a story · 13 points
HN discussionThe blog post will do: https://karpathy.bearblog.dev/auto-grade-hn/ ( https://news.ycombinator.com/item?id=46220540 )
Comment linking /auto-grade-hn/
on “HN Time Capsule”Submitted Chemical Hygiene as a story · 8 points
HN discussionI think there's an opportunity right now to reinvent public forum moderation with LLMs. Karpathy's recent post is going in the right direction I think: https://karpathy.bearblog.dev/auto-grade-hn/
Comment linking /auto-grade-hn/
on “Hacker News Alternative Where People Are Positive About AI”Submitted Chemical Hygiene as a story · 6 points
HN discussionInspired by Andrej Karpathy's project: https://karpathy.bearblog.dev/auto-grade-hn/
Comment linking /auto-grade-hn/
on “Auto-Grading Ten Years of Earnings Calls for Prescience and Delusion”Submitted Verifiability as a story · 6 points
HN discussionBy Karpathy: https://karpathy.bearblog.dev/the-append-and-review-note/
Comment linking /the-append-and-review-note/
on “Ask HN: Anyone else use a single gigantic .txt file as a notetaking solution?”Submitted Karpathy: LLMs are "ghosts," not "animals" as a story · 5 points
HN discussionSee also https://karpathy.bearblog.dev/the-append-and-review-note/
Comment linking /the-append-and-review-note/
on “Text Based Productivity”Submitted Finding the Best Sleep Tracker as a story · 4 points
HN discussionThe idea of HN being dismissive of impactful technology is as old as HN. And indeed, the crowd often appears stuck in the past with hindsight. That said, HN discussions aren't homogeneous, and as demonstrated by Karpathy in his recent blogpost "Auto-grading decade-old Hacker News", at least some commenters have impressive foresight: https://karpathy.bearblog.dev/auto-grade-hn/
Comment linking /auto-grade-hn/
on “2025: The Year in LLMs”Submitted Sequoia Ascent 2026 Summary as a story · 3 points
HN discussion
