Live data from Hacker News

Viewing profile — overactor

overactor

HN member
Joined
Sat, Nov 18, 2023, 12:35 PM UTC
HN karma
211
Public activity
22 items

About overactor

No profile information was provided.

Recent public activity

  1. comment
    Comment #38323949

    Oh, I didn't see your post. It's wild how much difference timing and slightly different wording can make. I couldn't have predicted which one of these posts would take off honestly…

  2. comment
    Comment #38321490

    Making accurate predictions in a specific domain doesn't imply understanding, sure. Universal autocomplete can make accurate predictions in all domains. Apples to oranges.

  3. comment
    Comment #38321445

    No human can solve the Riemann Hypothesis. Why do you expect an AI to do it before you consider it able to understand things?

  4. comment
    Comment #38321376

    I think this misses the point made by Hinton. The point is that, if a model is to reach a certain level of autocomplete, it needs to understand what it is talking about. Imagine th…

  5. comment
    Comment #38321273

    I think it's a little harsh to claim that the LLM didn't understand words. Sure it's far from perfect, but it mostly gives coherent answers. The AI is instructed to interpret each …

  6. comment
    Comment #38321238

    That was meant as tongue in cheek comment. Sorry if that didn't come across.

  7. comment
  8. comment
    Comment #38320208

    Yeah, the AI is far from deterministic.

  9. comment
    Comment #38320200

    That's definitely very worrying.

  10. comment
    Comment #38320192

    Also, I can't take any credit for creating the game. I'm just a fan sharing something cool.

  11. comment
    Comment #38320183

    You actually can use custom scenarios by clicking the pencil icon on the prompt selection screen.

  12. comment
    Comment #38320037

    I think I read that some companies are working on using LLMs to improve/generate dialogue from side characters.

  13. comment
    Comment #38319920

    I absolutely love that idea. The AI could absolutely pick a negative trait when the player survives. Maybe they gain a positive trait when they die? That way it might balance out a…

  14. comment
    Comment #38319836

    That's an interesting way of thinking about it. The AI definitely always rejects any attempt to make nothing happen.

  15. comment
    Comment #38319463

    I can't promise you this, because I haven't seen the actual code. But in the discord one of the devs has alluded to a bug occuring when the AI for some reason doesn't decide if the…

  16. comment
    Comment #38319439

    It's a bit hit and miss to be honest. You can throw some pretty wild stuff at it and often it reacts surprisingly well. On the other hand it also often crucially misunderstands thi…

  17. comment
    Comment #38319377

    Yeah, accepting death and prayer are both sort of like cheat codes.

  18. comment
    Comment #38319364

    A strong gust of wind could definitely knock you off balance enough to lift your foot if it's unexpected. But yeah, it doesn't really follow from the plan. If you're looking for a …

  19. comment
    Comment #38319091

    AFAIK AI players is on the roadmap, but the devs are mostly focusing on ironing out bugs right now.

  20. comment
    Comment #38319079

    You can pay alone, no problem. Though it's obviously more fun with people. The AI is pretty arbitrary and there are many ways to cheese the scenarios. I think that adds to the fun …

  21. comment
    Comment #38318890

    The game is still in beta and a bit buggy, but it's a great application of AI where its weaknesses can actually turn into strengths as it makes for funny output.

  22. story