Live data from Hacker News

Viewing profile — unignorant

unignorant

HN member
Joined
Thu, Jun 04, 2009, 6:41 PM UTC
HN karma
4,308
Public activity
494 items

About unignorant

Website: http://ethanfast.com

Substack: https://ethanfast.substack.com

Recent public activity

  1. comment
    Comment #49251872

    Yes, big fan of Unison (the system I described above follows its model for code hash identity) and I use a NixOS machine for most of my software work!

  2. comment
    Comment #49247298

    I'm also interested in this and made decent progress on a git-style content addressed image where everything is identified by hash and residency determines what's in memory. For ex…

  3. story
  4. comment
    Comment #48017957

    There are typical LLM voices and styles, just like human writers have differentiated voices and styles. And some common elements of the typical LLM style are distinct from humans I…

  5. comment
    Comment #48017802

    I had the same reaction, but the article is not AI-generated according to pangram, which I've generally found reliable. I wonder if LLM turns of phrase and even thought patterns ar…

  6. story
  7. comment
    Comment #47956015

    This isn't my project, but I shared it here because it has a few important ideas I've been thinking about in my own work. Effect type systems in particular are a really good fit fo…

  8. story
  9. story
  10. story
  11. comment
    Comment #47822183

    I agree, the more likely psychology of the Greg character is that he doesn't understand the way he presents himself in the pictures damns his surface level framing. You can really …

  12. comment
    Comment #46521249

    These days it's almost trivial to design a binder against a target of interest with computation alone (tools like boltzgen, many others). While that's not the main bottleneck to dr…

  13. comment
    Comment #44937811

    In another reply I gave an example of something you can do: https://news.ycombinator.com/item?id=44937774 I enjoy writing so a system like this would never replace that for me. But…

  14. comment
    Comment #44937774

    For flash you can get much better results by asking the system to first generate a detailed scaffold. Here's an example of some metadata you might try to generate before actually w…

  15. comment
    Comment #44937699

    I'm not sure I agree that the human stories felt original. I was pretty unimpressed with all of the stories except maybe 6, and even that one dealt in some common tropes. 5 had few…

  16. comment
    Comment #44937321

    Here are my notes and guesses on the stories in case people here find it interesting. Like some others in the blog post comments I got 6/8 right: 1.) probably human, low on style b…

  17. comment
  18. story
  19. comment
    Comment #44350335

    I really enjoyed this article but the claim of no literary fiction making the Publishers Weekly yearly top 10 lists since 2001 isn't really true: https://en.wikipedia.org/wiki/Publ…

  20. comment
    Comment #44140626

    yeah, it seems likely the underlying task here (one reasoning step away) was: replace as many fp32 operations as possible in this kernel with fp16. i'm not sure exactly how challen…

  21. comment
    Comment #44099894

    I do a lot of ML work too and recently gave NixOS a try. It's actually not too hard to just use conda/miniconda/micromamba to manage python environments as you would on any other l…

  22. comment
    Comment #43987021

    This technique doesn't actually use RL at all! There’s no policy-gradient training, value function, or self-play RL loop like in AlphaZero/AlphaTensor/AlphaDev. As far as I can rea…

  23. story
  24. story
  25. story