Live data from Hacker News

Viewing profile — rain1

rain1

HN member
Joined
Tue, May 15, 2018, 8:09 PM UTC
HN karma
1,127
Public activity
180 items

About rain1

No profile information was provided.

Recent public activity

  1. story
  2. comment
    Comment #46253724

    I've used Google Antigravity to write scripts to download and produce architecture diagrams for various LLMs from huggingface. It's pretty useful so I thought I'd share it. There's…

  3. story
  4. comment
    Comment #44444690

    The Gemma models are too small to be included in this list. You're right the T5 stuff is very important historically but they're below 11B and I don't have much to say about them. …

  5. comment
    Comment #44444658

    Yes but just purely in terms of entropy, you can't make a model better than GPT-4 by training it on GPT-4 outputs. The limit you would converge towards is GPT-4.

  6. comment
    Comment #44443289

    This is kind of related to the jack morris post https://blog.jxmo.io/p/there-are-no-new-ideas-in-ai-only he discusses how the big leaps in LLMs have mostly come - not so much from …

  7. comment
    Comment #44443274

    It's extremely interesting how powerful a language model is at compression. When you train it to be an assistant model, it's better at compressing assistant transcripts than it is …

  8. comment
    Comment #44443264

    I think that one thing that this chart makes visually very clear is the point I about GPT-3 being such a huge leap, and there being a long gap before anybody was able to match it.

  9. comment
    Comment #44443241

    This is really awesome. Thank you for creating that. I included a screenshot and link to the chart with credit to you in a comment to my post.

  10. comment
    Comment #44442808

    I can correct mistakes. > it somehow merged Llama 4 Maverick's custom Arena chatbot version with Behemoth I can clarify this part. I wrote 'There was a scandal as facebook decided …

  11. comment
    Comment #44442612

    I have corrected that. It was supposed to say "None of this document was written by AI." Thank you for spotting the error.

  12. story
  13. story
  14. comment
    Comment #41463926

    > Take care of your mental health How?

  15. comment
    Comment #40112534

    todsacerdoti is a spambot btw

  16. story
  17. comment
    Comment #37272487

    I don't understand this. Please can you point me to information about it?

  18. comment
    Comment #37272479

    The people that are astonished by this just need to learn why. It's not the function that is wrong, it's those people.

  19. comment
    Comment #36736793

    This is incorrect, the goats and car are behind doors. They are not inside cardboard boxes.

  20. comment
    Comment #36685467

    This is an example of hallucination. An LLM doesn't know anything about itself - it can be pre-prompted with facts about itself, but this is going to be an example of it just makin…

  21. comment
    Comment #36136066

    tell me you're posting from an armchair without telling me you're posting from an armchair

  22. story
  23. comment
    Comment #36101746

    what the actual fuck were they thinking uploading dolphin to steam??

  24. comment
    Comment #36092920

    Why don't they let us edit what the bot says? Could be useful.

  25. comment
    Comment #36031625

    This is the future of linux syscalls. Get on board with this or get left behind.