Live data from Hacker News

Viewing profile — sandkoan

sandkoan

HN member
Joined
Sun, Oct 11, 2020, 9:05 PM UTC
HN karma
128
Public activity
99 items

About sandkoan

https://govindgnana.com , https://blog.govindgnana.com

Recent public activity

  1. comment
    Comment #43958310

    DeepMind.

  2. story
  3. comment
    Comment #39997571

    See https://musiccontrolnet.github.io/web/

  4. comment
  5. comment
    Comment #39438429

    Ilya says this here: https://www.youtube.com/watch?v=AKMuA_TVz3A

  6. story
  7. comment
    Comment #38181983

    For anyone else interested, the paper he's referring to is "The Reversal Curse": https://arxiv.org/abs/2309.12288 .

  8. comment
    Comment #37908727

    For anyone who's curious, the paper in question, entitled, "Lost in the Middle: How Language Models Use Long Contexts" ( https://arxiv.org/abs/2307.03172 )

  9. comment
  10. comment
    Comment #37489588

    This is part of what we're doing at Automorphic. Building shareable, stackable adapters that you can compose like lego bricks.

  11. comment
    Comment #37128672

    This is what we did at Trex ( https://github.com/automorphic-ai/trex ). The tricky part is doing it quickly and efficiently.

  12. comment
    Comment #36821529

    Also using a similar method: https://github.com/automorphic-ai/trex Playground: https://automorphic.ai/playground

  13. comment
    Comment #36807525

    Relevant: Built this which generalizes to arbitrary regex patterns / context free grammars with 100% adherence and is model-agnostic — https://news.ycombinator.com/item?id=36750083…

  14. comment
    Comment #36769426

    Yeah, then it seems we agree. I was just pointing out that it's not necessary to finetune OSS models to behave like OpenAI functions if you're able to do something similar to what …

  15. comment
    Comment #36766808

    Ahh, no, the value of this isn't as much the model as it is the infrastructure enabling structure enforcement.

  16. story
  17. comment
    Comment #36763259

    https://news.ycombinator.com/item?id=36752991

  18. comment
    Comment #36755083

    You wouldn't actually want to, because you'd be losing generalizability, and it's a lot of unnecessary work. I think approach #1 outlined above is the better (more cost- and time-e…

  19. comment
    Comment #36754333

    Ahh, I've been meaning to try FLARE—was it a marked improvement over traditional RAG?

  20. comment
    Comment #36754259

    Thanks for the reminder—done!

  21. comment
    Comment #36753634

    This is model agnostic, actually—any model on HuggingFace is compatible. So if someone wanted to run this with their own model, they could.

  22. comment
    Comment #36753547

    Custom LLM—hence the self-hostability.

  23. comment
    Comment #36753292

    Costs add up surprisingly quickly. A quote-colon-space-quote combo alone is four tokens wasted. Now scale that up....

  24. comment
    Comment #36753284

    https://news.ycombinator.com/item?id=36753254 Does this help clarify?

  25. comment
    Comment #36753254

    The prompt is given to our model as a guiding aid (a suggestion), and the cfg is used to constrain the model to generate only tokens that abide by the schema (an enforcement). That…