Comment by tehnub

6 hours ago

Interesting exchange on the use of AI coding tools:

    curious how much did you write the code by hand of it?

    Karpathy: Good question, it's basically entirely hand-written (with tab autocomplete). I tried to use claude/codex agents a few times but they just didn't work well enough at all and net unhelpful, possibly the repo is too far off the data distribution.

https://x.com/karpathy/status/1977758204139331904

31 comments

tehnub

Reply
gyomu  5 hours ago

> the repo is too far off the data distribution

ah, this explains why these models have been useless to me this whole time. everything i do is just too far off the data distribution!

  • SchemaLoad  5 hours ago

    Everything is unless your app is a React todolist or leatcode questions.

    • notatoad  4 hours ago

      people say this like it's a criticism, but damn is it ever nice to start writing a simple crud form and just have copilot autocomplete the whole thing for me.

      4 replies →

    • SeanAnderson  4 hours ago

      or a typical CRUD app architecture, or a common design pattern, or unit/integration test scaffolding, or standard CI/CD pipeline definitions, or one-off utility scripts, etc...

      Like 80% of writing coding is just being a glorified autocomplete and AI is exceptional at automating those aspects. Yes, there is a lot more to being a developer than writing code, but, in those instances, AI really does make a difference in the amount of time one is able to spend focusing on domain-specific deliverables.

      2 replies →

  • teleforce  2 hours ago

    I wonder if the new GenAI architecture namely DDN or distributed discrete networks being discussed recently can outperform the conventional architecture of GAN and VAE. As the name suggests, it can provide multitude of distributions for training and inference purposes [1].

    [1] Show HN: I invented a new generative model and got accepted to ICLR (90 comments):

    https://news.ycombinator.com/item?id=45536694

rootusrootus  5 hours ago

That is a good thing to hear from someone as reputable as Karpathy. The folks who think we're on the cusp of AGI may want to temper their expectations a bit.

I do love Claude Code, because one thing I periodically need to do is write some web code, which is not my favorite type of coding but happens to have incredibly good coverage in the training data. Claude is a much better web developer than I am.

But for digging into the algorithmic core of our automation tooling, it doesn't have nearly as much to work with and makes far more mistakes. Still a net win I'm happy to pay for, even if it's never anything more than my web developer slave.

  • vunderba  3 hours ago

    100%. I find the "LLMs are completely useless" and the "LLMs will usher in a new era of messianic programming" camps to be rather reductive.

    I've already built some pretty large projects [1] with the assistance of agentic tooling like Claude Code. When it comes to the more squirrely algorithms and logic, they can fall down pretty hard. But as somebody who is just dreadful at UI/UX, having it hammer out all the web dev scaffolding saves me a huge amount of time and stress.

    It's just a matter of tempering one's expectations.

    [1] https://animated-puzzles.specr.net

    • meowface  37 minutes ago

      >and the "LLMs will usher in a new era of messianic programming" camps

      Well, this one might still be borne out. It's just silly to think it's the case right now. Check in again in 10 years and it may be a very different story. Maybe even in 5 years.

      1 reply →

  • bdangubic  5 hours ago

    > But for digging into the algorithmic core of our automation tooling

    What I find fascinating is reading this same thing in other context like “UI guru” will say “I would not let CC touch the UI but I let it rip on algorithmic core of our automation tooling cause it is better at it than me…”

    • Filligree  4 hours ago

      Both can be true. LLMs tend to be mediocre at (almost) everything, so they're always going to be worse than the user at whatever the user is an expert in.

      But 'mediocre' isn't 'useless'.

      1 reply →

SeanAnderson  5 hours ago

This makes sense, right? It's a relatively novel thing to be writing. I don't find it to be a damning remark like other comments here seem to be concluding.

If anything, the fact that Karpathy reached towards Claude/Codex in an attempt to gain value is indicative that, in previous coding efforts, those tools were helpful to him.

  • simonw  5 hours ago

    Yeah, if your goal is "build the tightest 8,000 line implementation of training an LLM from scratch, with a focus on both conciseness and educational value" I don't think it's particularly surprising that Claude/Codex weren't much help.

  • bringmeiron  4 hours ago

    > If anything, the fact that Karpathy reached towards Claude/Codex in an attempt to gain value is indicative that, in previous coding efforts, those tools were helpful to him.

    This is good for bitcoin.