Comment by throw10920 | Hacker News Reader

Comment by throw10920 | Hacker News Reader

Parent Full thread

> Words have meaning - you cant just redefine them because you want to.

You are redefining words. The consensus among people who work in this space is that "distilling" is what's actually going on here.

> who are just as anti-Chinese as Anthropic

Conflating criticism of IP theft with being "anti-Chinese" is a standard PRC influence playbook technique.

And furthermore, OpenAI's market strategy is to win through regulatory capture. They are financially incentivized for Anthropic to be distilled by PRC labs and to be undercut by open models. Their claim about Kimi not being explainable due to distillation is not a factual claim - it's marketing from a company owned by Sam Altman.

Although, it does conclusively disprove your claim about the meaning of distillation, because you cannot say that "Kimi can't be explained by distilling" unless the consensus definition of "distillation" is such that it could be done on the summarized reasoning traces that Anthropic models expose.

> you cannot say that "Kimi can't be explained by distilling" unless the consensus definition of "distillation" is such that it could be done on the summarized reasoning traces that Anthropic models expose

You can interpret it as you choose, but a much more obvious reason he [OpenAI's Dean Ball] might say it can't be distilled is because it can't be distilled. You can't distill alcohol out of orange juice.

> because it can't be distilled

...and, as everyone in the frontier labs knows, this is a lie, because that's not how distillation is defined.

I know that I won't convinced you, because you're quite possibly a PRC agent, but for all the other HN readers coming to this thread in the future to look at this failure of propaganda: just ask a model.

User: according to standard LLM lab parlance, can you "distill" one model from another if the model being distilled from does not expose a thinking trace?

GPT-5.6 Sol: Yes. In standard LLM terminology, you can distill one model from another even if the teacher model does not expose a chain-of-thought or "thinking trace."

Sonnet 5: Yes. "Distillation" broadly means training a student model to replicate a teacher model's outputs (or output distribution), and this doesn't require access to the teacher's chain-of-thought.

That's all she wrote. You're lying, and even the models know it. If you want to continue to discredit your account, go ahead :)

When your mom tells you it's time to go to bed, do you respond "You're lying! You're a communist! Boo hoo, I'm going to tell dad!"

Just curious.

Keep discrediting your account. I know that I can't convince a propagandist, but you just keep on further damaging your own reputation and argument for other HN readers every time you respond like this and ignore evidence that I've linked :)

Reply on news.ycombinator.com