Live data from Hacker News

Viewing profile — theowaway213456

theowaway213456

HN member
Joined
Sat, Feb 21, 2026, 5:17 PM UTC
HN karma
93
Public activity
54 items

About theowaway213456

No profile information was provided.

Recent public activity

  1. comment
    Comment #49129721

    errgroup has a SetLimit function to control the max number of concurrent go routines running at once.

  2. comment
    Comment #49109953

    > Like who really runs frontier LLMs at `max`? Umm what? Lots of people do

  3. comment
    Comment #48994800

    But how else am I supposed to know when we've reached AGI, until I see an absolutely flawless pelican? All of the pelicans so far have had really weird flaws / quirks so I am alway…

  4. comment
    Comment #48992958

    You can also build your own harness for Claude, right? I think that's not against their ToS? Not saying it's ideal, just saying it's an option

  5. comment
    Comment #48909774

    This sort of take is so tired and boring, and frankly has zero grounding in reality. "LLMs will never " is constantly being disproven every time they scale up to the next 10X and a…

  6. comment
  7. comment
    Comment #48662158

    This seems like more competition for Cerebras? Am I understanding correctly?

  8. comment
    Comment #48644283

    Obviously the approach you mentioned has the downside of two server round-trips being necessary while the QUERY request only requires a single round-trip. Not to mention the two-re…

  9. comment
    Comment #48629809

    Every time you write a test that handles some data, you write an assertion about how much data is handled? Come on, this is such an easy thing to forget to test. Don't act like the…

  10. comment
    Comment #48624798

    TL;DR don't have your agent write skills using only its latent knowledge, otherwise you may as well not use a skill in the first place and let it summon that latent knowledge on th…

  11. comment
    Comment #48619995

    Claiming that something is someone's "entire personality" is extremely reductive and definitely hostile

  12. comment
    Comment #48431047

    Yep that's the first time I noticed it. The pocket was also numbered for me as well

  13. comment
    Comment #48431022

    Not a single mention of prompt caching in this article, which is a massive benefit of append-only context.

  14. comment
    Comment #48427828

    Certain entities seem to be displayed as numbers for me, like "You received a 6" etc when getting my first potion. Anyone else seeing this bug?

  15. comment
  16. comment
    Comment #48186283

    This implementation is better than stdlib's implementation in my opinion, since it respects context: https://github.com/janos/singleflight

  17. comment
    Comment #48103336

    Old news - both of these vulnerabilities made top headlines on HN. This post isn't contributing much. (Tangentially, the title of this article is egregiously difficult to parse.)

  18. comment
    Comment #48045147

    It's very hard to use on mobile. When clicking a graph node, something happens kind of far down in the viewport, which I didn't notice at first. Also clicking "Open post" doesn't s…

  19. comment
    Comment #47902951

    This feels like a suboptimal solution to me because I personally like to keep comments in "unresolved" state so that they remain visible and other folks can weigh in on them if the…

  20. comment
    Comment #47870310

    Yup. No matter how much you tell it to keep things simple, modular, crisp, whatever, it generates tons of garbage much too often.

  21. comment
    Comment #47857706

    lol after reading your first sentence I literally thought to myself "this sounds like the type of person who never closes their browser tabs"

  22. comment
    Comment #47833944

    In my experience, this mistake happens all the time for native English speakers born in the US.

  23. comment
  24. comment
    Comment #47833880

    If we're allowed to make modifications here then it should really be lose => looze and loose => luce

  25. comment
    Comment #47743097

    I 100% understand why you are using a subscription-based model. It makes sense, and I agree it's the most honest model given that you have to continually support it and you don't w…