Rendered at 14:57:29 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
delichon 33 minutes ago [-]
If you want to believe that the success of Kimi is about distillation attacks, ignore this.
Parfait__ 23 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 13 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.
bratao 13 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.
senko 32 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).
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 hours 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 58 minutes ago [-]
Same with DeepSeek papers, they are a joy to read.
senko 31 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)?
Basically, they want IP protection for Claude. This is a nakedly hypocritical stance, but completely understandable from a company-needs-to-make-money standpoint.
[0] https://arxiv.org/abs/2607.24653
As it's 9 months old and they just had a major model release
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.