News for hackers. Stuff that matters.
Re:Stealing Reasoning Traces from Proprietary LLM APIs by varenc on Tuesday August 11, 2026 @10:56PM (#49267344)
This article shows that when Kimi3's chain of thought is prefilled to match Opus's, the rest of the chain of thoughts Kimi3 outputs very closely aligns with Opus's. That seems strong evidence that Kimi3 is partly a distillation of Opus. And Kimi3 is not a small model. No doubt a lot of hard work went into Kimi, but seems clear that distillation was used effectively as well.

(though maybe there's another interpretation of the thought alignment?)

Re:Stealing Reasoning Traces from Proprietary LLM APIs by wonnage on Tuesday August 11, 2026 @11:43PM (#49267614)
Didn’t Kimi3 release a week before opus 5?
Re:Stealing Reasoning Traces from Proprietary LLM APIs by Otterly99 on Wednesday August 12, 2026 @04:38AM (#49269412)
They compare it to Opus 4.8 in the article, which has been available for a few months now.
Re:Stealing Reasoning Traces from Proprietary LLM APIs by irthomasthomas on Wednesday August 12, 2026 @10:17AM (#49272764)
But they don't perform the same test on other models as far as I could tell? So we don't lnow if this is peculiar to kimi models or not.