Comment by giancarlostoro
14 hours ago
To be fair, I assume they want to hide that not from their customers, but adversaries who use the way Claude models think and reason to refine their own models.
14 hours ago
To be fair, I assume they want to hide that not from their customers, but adversaries who use the way Claude models think and reason to refine their own models.
I have a hard time believing whatever prompts get Claude to reason can stay relevant secret sauce for long anyways. It’s not hard to A/B test something that gets you close enough, and it’s not Ike anthropic has uncovered the global optima of reasoning prompts.
That's their motivation, for sure. But it's also unambiguously making their product worse and harder to use legitimately. Which pushes customers further towards use of open weight models which don't have these restrictions. I don't think this is a fight they're going to win.
It's also hard to have sympathy for them - they want to protect their IP, sure. But their IP was built on a corpus of dubious legal provenance. And even if the courts decide their training data are legal, most of the authors of the data would disagree. There was no consent given.
I think LLM's are great - don't get me wrong. I'm glad they were built the way they were, because it's unlocking an amazing new world. But I just don't have sympathy for the "I stole this and now it's mine so you can't steal it" argument behind concealing reasoning traces.
I think this whole distillation argument is between fully overblown and bogus.
In any case, highly misunderstood.
I don't really want the models I use learning from Claude at this point. Open weight models of similar scale are available now too, so I expect this "distillation"/"stealing" chatter to wind down.
Maybe, but that's sort of begging the question that those open weight models aren't significantly trained using "distillation"[0]
[0] not technically distillation. https://thomasdullien.github.io/posts/2026-06-15-rl-economic...
distillation is a minor piece of training data, you have to have a good foundation for it to be helpful, and even if you have good traces, you need a good RL reward scheme at the point it is used (very challenging)