Live data from Hacker News

Viewing profile — fovc

fovc

HN member
Joined
Thu, Oct 09, 2014, 5:50 AM UTC
HN karma
1,165
Public activity
411 items

About fovc

No profile information was provided.

Recent public activity

  1. comment
  2. comment
    Comment #46152812

    Łukasz Kaiser basically confirmed it in a podcast: https://youtu.be/3K-R4yVjJfU?si=JdVyYOlxUbEcvEEo&t=2624 > Q: Are the releases aligned with pre-training efforts? > A: There used …

  3. comment
    Comment #46023125

    > I also think it’s important to notice that a lot of these challenges they happen with humans too. The concept of prompt injection isn’t that different from social engineering, ri…

  4. story
  5. comment
    Comment #45157833

    Crossover from the other front page article. I tested out ChatGPT5 search mode and there are some good sources! https://chatgpt.com/s/t_68bd82908c0c8191b142b860ff91c9dc

  6. comment
    Comment #44306163

    Very nice! For other readers, vc is short for verification condition and wp is short for weakest precondition.

  7. comment
    Comment #43369083

    I wonder if the error propagation problem could be solved with a “branching” generator? Basically at every token you fork off N new streams, with some tree pruning policy to avoid …

  8. story
  9. comment
    Comment #43189538

    Or see the explanation in video form here: https://m.youtube.com/watch?v=d0HJvGSWw8A Mamba has been discussed a lot here, and this seems like a promising line of inquiry for improv…

  10. story
  11. comment
    Comment #43149769

    And also make sure that slot is a symbol in the correct package. Or do like Elisp and do without packages but then have a 16 character prefix

  12. comment
    Comment #43144752

    Having the data structures is nice and all, but using them is kind of painful. They are certainly second class. Having to use accessor functions or destructuring macros instead of …

  13. comment
    Comment #43096336

    Sparse attention essentially combines 3 types of attention optimizations: 1. Compression of the query input vectors to reduce the size of the KV cache 2. Selectively computing unco…

  14. story
  15. story
  16. comment
    Comment #43048263

    Ah thanks for the clarification! Do you happen to know if Nile/Gezira went anywhere?

  17. comment
    Comment #43020600

    Great to see this is alive and progressing! I believe Ohm started life in Alan Kay’s research group, to build a graphical OS and office suite in 10k lines of code. I found this tal…

  18. story
  19. comment
    Comment #42807515

    > I feel like I'm taking crazy pills when I read about others' experiences. Surely I am not alone? You're not alone :-) I asked a very similar question about a month ago: https://n…

  20. comment
    Comment #42554770

    The “pair programming” approach with good models is just slow enough that I lose focus on each step. The faster models I’ve tried are not good enough except for straightforward thi…

  21. comment
    Comment #42552653

    I still don’t understand how people are getting value out of AI coders. I’ve tried really hard and the commits produced are just a step up from garbage. Writing code from scratch i…

  22. comment
    Comment #42543795

    Makes a ton of sense! Is this for completions, patches, or new files?

  23. comment
    Comment #42528248

    Maybe this? https://www.cis.upenn.edu/~bcpierce/tapl/

  24. comment
    Comment #42512099

    Agree it’s not a toy. AWS implemented a large chunk of IAM in Dafny. Though IIRC they have their own non-public compiler to Java

  25. comment
    Comment #42512086

    It’s also useful in typed languages to introduce an existentially quantified type