Live data from Hacker News

Viewing profile — calderknight

calderknight

HN member
Joined
Tue, Jan 17, 2023, 9:45 PM UTC
HN karma
207
Public activity
230 items

About calderknight

calderknight.net

Recent public activity

  1. comment
    Comment #40325313

    Yeah, if going that route the answer to the OP is "most people aren't using it for Lisp".

  2. comment
    Comment #40314115

    Mystery solved! The answer to your OP is that the reason anyone can trust ChatGPT for code is that they use a much better model than the one you're using! GPT-3.5 is ancient and wa…

  3. comment
    Comment #40312686

    ChatGPT is just the brand. I guess you're using GPT-4, but if you're using the default model (GPT-3.5) that would certainly explain below-expectation results.

  4. comment
    Comment #40304974

    That's something you can easily prompt for, too.

  5. comment
    Comment #40303219

    What model were you using? What prompt did you use? You can learn to trust it for some tasks that it's reliably good at. But for the most part, you don't trust it - you read throug…

  6. comment
    Comment #40260745

    a few million years ago there were land mammals https://en.wikipedia.org/wiki/Saint_Bathans_mammal

  7. comment
  8. comment
    Comment #40204219

    leagues ahead of gpt-4-turbo-2024-04-09

  9. comment
    Comment #40190809

    A USA made product

  10. comment
    Comment #39831689

    To be clear, the best available version of Gemini has barely caught up with what OpenAI released over a year ago. Google's a year behind. They haven't really caught up.

  11. comment
    Comment #39725455

    I don't think there's a contradiction between being something that just generates text and being something that does have thought processes and intention.

  12. comment
    Comment #39517553

    Not logical. It doesn't follow from the assumption that the host would not pose the question "Hey, here's the car, wanna switch?" that the contestant would automatically lose. You …

  13. comment
    Comment #39517528

    You can imagine factors other than his personality, but they're all equally as speculative. Additional rules to the game, for example.

  14. comment
    Comment #39515996

    If the format of the game allows him to show the car to the player, how could his personality not enter into it? In every case where the player picks a goat-door, the host will be …

  15. comment
    Comment #39515779

    I don't think your interpretation of the sentence is sensible. The sentence mentions that the host knows what's behind the doors. So, if he is allowed to open the door with the car…

  16. comment
    Comment #39515711

    That's clear. Otherwise the question would just be about speculating on the host's personality.

  17. comment
    Comment #39515652

    It's simple. To begin with it's 1/3 your pick is right. You know that a goat will be revealed. So it's absurd to suppose that the fact that a goat is revealed has increased the pro…

  18. comment
  19. comment
    Comment #39427019

    I would guess the new chatbots have already stolen a bit of the market.

  20. comment
    Comment #39427009

    worldcoin integration

  21. comment
  22. comment
    Comment #39323527

    It does overlap a lot. Accelerationism is a cosmismist viewpoint and rejects the orthogonality thesis. In other words, it favours the construction of ASI even if it means the extin…

  23. comment
    Comment #39303170

    I don't get interested when something says "I'm a really useful x". I get interested when it says "I'm a really useful x because y". You're the x I've been waiting for? Great, why?…

  24. comment
    Comment #39301414

    is there an API? if so, how expensive is it to use?

  25. comment
    Comment #39284921

    The students are using it anyway, so Oslo decided that teaching students to use it would be the best path. That way they can teach the students about the hallucinations and about e…