Live data from Hacker News

Viewing profile — graemefawcett

graemefawcett

HN member
Joined
Sun, Oct 22, 2023, 11:58 AM UTC
HN karma
21
Public activity
41 items

About graemefawcett

No profile information was provided.

Recent public activity

  1. comment
    Comment #48086940

    The other cases are the original request is still in flight or never occurred. The former case was explained by the prior comment, one request is processed, the other is returned b…

  2. comment
    Comment #47635809

    Stateless router to router with lossy scratchpad is a step up, still not going to ask it to check my Lisp. That's what linters are for

  3. comment
    Comment #47635576

    RAG is like when you want someone to know something they're not quite getting so you yell a bit louder. For a workflow that's mainly search based, it's useful to keep things ground…

  4. comment
    Comment #47618642

    It's not just an issue of tokenization, it's almost a category error. Lisp, accounting and the number of r's in strawberry are all operations that require state. Balancing ((your)(…

  5. comment
    Comment #47364559

    Exactly. They've implemented a VM inside a transformer, turned an O(1) memory access call into O(n), optimized it down to O(log n) and wrote a post about how smart they are. It's a…

  6. comment
    Comment #47364482

    Basically just madlibs - the models generate intermediate tokens that help predict a better answer based on training (RLHF & otherwise). They tend to look like "reasoning" because …

  7. comment
    Comment #47237700

    I believe that's I and the paper are both saying as well. The LLM is pure routing, the constraints currently are located elsewhere in the system. In this case, both the constraints…

  8. comment
    Comment #47235282

    This is exactly how problem solving works, regardless of the substrate of cognition. Start with "all your questions contained in randomness" -> the unconstrained solution space. Th…

  9. comment
    Comment #47234960

    Connecting them is easy, one is the math of the exchange and one of the state machine. A better question might be why no one is paying more attention to Barandes at Harvard. He's b…

  10. comment
    Comment #46832190

    [flagged]

  11. comment
  12. comment
    Comment #46591102

    I think the biggest benefit is bandwidth more so than efficiency. This gives you multiple streams to mux which and a means to control their mixing. The biggest innovation I think m…

  13. comment
    Comment #46572740

    Are you aware that there are certain members of your very own species that are as intelligent as you or I, who lack those qualia. Non standard cognitive architectures are already c…

  14. comment
    Comment #46568880

    I took that idea just as far as I could and landed here https://zenodo.org/records/18181233 It parses the AST out of it and then has a play We're using it as an agentic control pla…

  15. comment
    Comment #46548010

    We propose SyneState: a communication prosthetic built on DeepSeek's Manifold-Constrained Hyper-Connections (mHC) architecture. By parameterizing cross-channel mixing as a doubly-s…

  16. story
  17. comment
    Comment #46345655

    Besides, if everyone could paint the Sisten Chapel, then we'd have works equivalent to the Sistene Chapell everywhere. Why is that a problem? That to me sounds like the opposite of…

  18. comment
    Comment #46345580

    Is art then just the outcome? The artifact that was produced? What's your criteria then for who is allowed to produce art? If allowing everyone to create it lessens its value such …

  19. comment
    Comment #46333482

    I've been doing it for months, it's lovely https://tech.lgbt/@graeme/115749759729642908 It's a stack based on finishing the job Jupyter started. Fences as functions, callable and c…

  20. comment
    Comment #46321334

    I had a sickie yesterday with nothing better to do than attempt to prove isomorphism across domains Like drawing lines on a mids menu but for grown ups when the price is right isn'…

  21. comment
    Comment #46320775

    Two systems are isomorphic when they admit the same morphisms—when the set of valid transformations applicable to one equals those applicable to the other. If Hom(X, DNS) ≅ Hom(X, …

  22. story
  23. story
  24. comment
  25. story