6 comments

  • pooyamo 1 minute ago
    Does any expert in the field know whether it is really the case that this intelligence we are seeing with frontier models is an "emerging" phenomena, only coming up when the architecture is scaled?

    Like isn't it weird that the 1 million parameter model with the same architecture can't solve basic puzzles but suddenly the 1 trillion parameter can conjure up counter-examples for the Jacobian conjecture?

    It's unintuitive since, to the best of my knowledge, one of the basic tenants of algorithm development was that you can't just brute-force your way towards a solution for some complex problems, e.g. naive sorting algorithms suddenly won't beat quicksort if you put more processing to them, but in the modern LLM scene it seems people are in a race to scaling up, experimenting empirically and hoping the same algorithm/architecture comes to a solution.

  • delichon 39 minutes ago
    If you want to believe that the success of Kimi is about distillation attacks, ignore this.
    • Aurornis 0 minutes ago
      You can’t build a frontier model with one single thing. This is an incremental improvement but it doesn’t explain the entire success of the model. The training set is immensely important, regardless of how you feel about distillation.
    • WhitneyLand 2 minutes ago
      False dichotomy right?

      Are Chinese labs impressively innovating? Clearly.

      However this doesn’t rule out possible gains due to distillation.

      I don’t know the degree of the latter but both things could certainly be true.

    • Parfait__ 30 minutes ago
      I stil don't understand them. I want the US to "win the AI race" but I have trouble understanding how most of all inventions today aren't "distillations" of past knowledge. Is Anthropic claiming the data they stole as trade secrets?
      • fwip 20 minutes ago
        Anthropic is claiming that training an LLM to mimic another LLM is materially different and worse than slurping up stuff written by humans (even if that material is stolen).

        Basically, they want IP protection for Claude. This is a nakedly hypocritical stance, but completely understandable from a company-needs-to-make-money standpoint.

  • senko 39 minutes ago
    Old but relevant: if you read the recently-released Kimi K3 paper[0], you'll see that it's heavily based on Kimi Linear discussed here, scaling it up and adding a bunch more things (like native vision and RL improvements).

    [0] https://arxiv.org/abs/2607.24653

  • bratao 20 minutes ago
    I started creating internal models using it, then the Gated Deltanet 2 came out( https://arxiv.org/abs/2605.22791), and it seems like an evolution of it in expressiveness. And in our tests it is really better than.
  • jasonjmcghee 2 hours ago
    (2025)

    As it's 9 months old and they just had a major model release

    • throwa356262 1 hour ago
      For K3 read this instead: https://arxiv.org/abs/2607.24653

      The main contribution of the K3 paper is Stable LatentMoE. Like some other models it compresses data sent between layers, which puts certain requirements on the router. K3 improves performance by using a more balanced expert selection strategy.

      • mcbuilder 1 hour ago
        Compared to the Opus 5 "model card", which read like a standard Anthropic set of alignment principles and safety concerns, this presents a plethora of useful technical details that advances the state of the art.
        • throwa356262 1 hour ago
          Same with DeepSeek papers, they are a joy to read.
      • senko 37 minutes ago
        Not an expert, but looks like they did a lot more work on the RL part (9 expert models, full sandbox access for agentic tasks, etc)?
    • cptcobalt 1 hour ago
      Rather under-discussed back then: https://news.ycombinator.com/item?id=45766937
    • GaggiX 1 hour ago
      I believe OP posted it because the new Kimi K3 has 69 KDA layers (the rest are 24 Gated MLA), I think previous large Kimi models had only MLA layers.
      • yorwba 1 hour ago
        It's not the same KDA as used in Kimi Linear, though.
        • GaggiX 58 minutes ago
          What's the difference? They are both called Kimi Delta Attention.
  • Topology1 53 minutes ago
    Another banger from Zhang et. al