Live data from Hacker News

Viewing profile — lgessler

lgessler

HN member
Joined
Tue, Sep 29, 2015, 6:26 AM UTC
HN karma
1,712
Public activity
435 items

About lgessler

https://lgessler.com

Recent public activity

  1. comment
    Comment #49198024

    I'm confused. I think you're confusing Gemini and Gemma. Gemini is Google's frontier offering which is closed-weight, API-only, like most frontier models. Gemma is Google's open-we…

  2. comment
  3. comment
    Comment #48949319

    You're saying it's important to have up-to-date facts stored in parametric knowledge? It seems to me like that's grown less and less important as agentic capabilities have grown. E…

  4. comment
    Comment #48782799

    Accuracy isn't a meaningful metric here without reference to a specific task.

  5. comment
    Comment #48557171

    Not that this really takes away from the substance of the article, but the first two paragraphs are giving heavy Claude smell. Semicolons, em dashes, "That sequencing matters"... I…

  6. comment
    Comment #48392299

    Raphaël Millière has a very useful term for this kind of vacuous dismissal, the redescription fallacy ( https://arxiv.org/pdf/2401.03910 , page 9): > Recent debates have been cloud…

  7. comment
    Comment #47868161

    I'll be really interested to hear qualitative reports of how this model works out in practice. I just can't believe that a model this small is actually as good as Opus, which is ru…

  8. comment
    Comment #47646092

    Is Java or Haskell any closer to human language?

  9. comment
    Comment #47416925

    Has everyone always nailed their implementation of every program on the first try? Of course not. Probably what happens most times is you first complete something that sorta works …

  10. comment
    Comment #47383111

    I know this is mostly about keyword substitution but it still tickles me that you still write f(x) in this language and not (x)f given that Korean is SOV but I guess that's just ho…

  11. comment
    Comment #46984011

    Let's be real here, regardless of what Boris thinks, this decision is not in his hands.

  12. comment
  13. comment
  14. comment
    Comment #45076319

    Novels are fictional too. So long as they're not taken too literally, archetypes can be helpful mental prompts.

  15. comment
    Comment #44966516

    If you're really just doing traditional NER (identifying non-overlapping spans of tokens which refer to named entities) then you're probably better off using encoder-only (e.g. htt…

  16. comment
    Comment #44887204

    I recommend having a look at 16.3 onward here if you're curious about this: https://web.stanford.edu/~jurafsky/slp3/16.pdf I'm not familiar with Whisper in particular, but typicall…

  17. comment
  18. comment
    Comment #44527453

    In my (poor) understanding, this can depend on hardware details. What are you running your models on? I haven't paid close attention to this with LLMs, but I've tried very hard to …

  19. comment
  20. comment
  21. comment
    Comment #43640148

    Sure, this is a common sentiment, and one that works for some courses. But for others (introductory programming, say) I have a really hard time imagining an assignment that could n…

  22. comment
  23. comment
    Comment #43639035

    I'm a professor at an R1 university teaching mostly graduate-level courses with substantive Python programming components. On the one hand, I've caught some students red handed (Ch…

  24. comment
    Comment #42662700

    > Fermentation is completely stopped in a regular fridge, you need higher temperature for fermentation. My understanding as a hobbyist brewer and fermenter is that this is not true…

  25. comment
    Comment #42591408

    I think this is both a harmful and irrational attitude. Why focus on some trivial mechanical errors and disparage the authors for it instead of the thing that is much more importan…