Live data from Hacker News

Viewing profile — rodoxcasta

rodoxcasta

HN member
Joined
Thu, Apr 13, 2023, 6:26 PM UTC
HN karma
154
Public activity
39 items

About rodoxcasta

No profile information was provided.

Recent public activity

  1. comment
    Comment #41184889

    Wait, this 'Agents' thing seems to be just a way to couple a system prompt and temperature to a model, that's it? What's the difference from sending the system prompt in the api ca…

  2. comment
    Comment #40813380

    > Additionally, when people use CriticGPT, the AI augments their skills, resulting in more comprehensive critiques than when people work alone, and fewer hallucinated bugs than whe…

  3. comment
    Comment #39281925

    > Notices: Apple's rights in the attached weight differentials are hereby licensed under the CC-BY-NC license. Apple makes no representations with regards to LLaMa or any other thi…

  4. comment
    Comment #38976699

    The title is wrong: this is about ChatGPT Plus, not GPT-4. Specifically, the author is investigating (possible) changes in the system prompt and tools available to the model in the…

  5. comment
    Comment #37105228

    That, I always have difficulty with these types of replies. What should you do when someone, in a serious discussion, says that the Earth is flat, with a straight face? Are they mo…

  6. comment
    Comment #37092177

    on my firefox it didn't work, just keep asking to connect a security token, with no other option. Firefox 116, Ubuntu 20.04, had an Yubikey in the past, never used passkey. I think…

  7. story
  8. comment
    Comment #37007044

    AFAIK the main difference is in certain provisions designed to block the use of patents to restrict the fundamental freedoms that GPL allows to the user. The main drawback is that …

  9. story
  10. comment
    Comment #36966355

    While the article has an obvious point of view, it cites other people defending their view , with plenty of links, and even the response from Harvard ('we don't comment individual …

  11. comment
    Comment #36965619

    Is someone using some old phone, but with a recompiled kernel, to support standard linux features, like docker? It's possible in theory, but still didn't found someone doing it. Se…

  12. comment
    Comment #36960222

    If your loss goes from 5% to 1%, you have to deal with 80% less heat. So you can make 3x smaller motors. All the powertrain of these machines will be hugely simplified. That's no s…

  13. comment
    Comment #36927133

    For inference, at least locally, the bottleneck is usually the memory bandwidth (and quantity, of course). I hope that AI hype lead us to more memory and more memory bandwidth, bec…

  14. story
  15. comment
    Comment #36843294

    That's an interesting math. I don't think they are using 4 bits, or even 8. My bet would be with 16 bits. (Bear in mind that's just speculation, for "math's sake"). So we are talki…

  16. comment
    Comment #36822213

    The thing is, you (we) only identify chatGPT generated content when it has that generic voice. Maybe there's a lot more generated content here, but it isn't so obvious. It's a sele…

  17. comment
    Comment #36816263

    If the weights are not copyrighteable, you don't need a licence do use them, they are just data. There's not a right to infringe if these numbers have no author. Of course, to use …

  18. story
  19. story
  20. comment
    Comment #36017038

    > The sequence of these two threads is just too perfect. Almost likely someone is trying to make a point. Exactly! Almost every weak point that Knuth commented is fixed in GPT4 ans…

  21. story
  22. comment
    Comment #35924002

    > There's no underlying theory of mind here. Actually, there's some experimental evidence that GPT4 have a Theory of Mind as good as humans, maybe better. https://arxiv.org/abs/230…

  23. comment
    Comment #35922471

    They focus the immune system on the tumor by teaching it to identify some "neoantigens" in the tumor. Turns out that tumors express various strange proteins in their cell wall, I s…

  24. comment
    Comment #35887852

    They record the brain language processing via fMRI and the activations of some AI models during language tasks, then create a linear map between them. Then they use that map to try…

  25. comment
    Comment #35887497

    Abstract The neuroscience of perception has recently been revolutionized with an integrative modeling approach in which computation, brain function, and behavior are linked across …