2 comments

  • jasonjmcghee 1 hour ago
    (2025)

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

    • throwa356262 37 minutes 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 21 minutes 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 17 minutes ago
          Same with DeepSeek papers, they are a joy to read.
    • cptcobalt 34 minutes ago
      Rather under-discussed back then: https://news.ycombinator.com/item?id=45766937
    • GaggiX 57 minutes 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 12 minutes ago
        It's not the same KDA as used in Kimi Linear, though.
        • GaggiX 10 minutes ago
          What's the difference? They are both called Kimi Delta Attention.
  • Topology1 5 minutes ago
    Another banger from Zhang et. al