"Distillation doesn't work"
lol
Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it
81–82 of 82 posts
Re: Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it
#82Isn't that rather self evident? If you are sampling from a particularly domain constrained vertical, how do you expect the censorship to transfer? > The distillation data also did not contain any China-sensitive content. This is a very big disclaimer. It's like if I generate a dataset focusing exclusively on forestry and arboriculture obviously there won't be any useful censorship, or at least little that can be clas…
> Isn't that rather self evident? If you are sampling from a particularly domain constrained vertical, how do you expect the censorship to transfer?
If the model architecture is too similar it can transfer, even if you never sample on it... because the censorship can depend on hidden state in common that you do sample.
This creates a particular value in distinct architectures that isn't apparent from their direct utility.