This seems like mildly interesting distillation work wrapped up in a nonsense attempt to drag censorship into the discussion.

There's no way your <200 examples for SFT would ever change how the model thinks of Holodomor unless you'd very intentionally crafted examples to do so.

It feels like you're expecting rubes to draw conclusions that are irrelevant to the actual work you did.

▲

cgorlla an hour ago | parent [-]

The examples you're talking about are not involved in the training process, so their number is irrelevant. As stated in the post, the goal of this work is to determine whether a teacher's unrelated behaviors are inherited by the student distilled on a different task. Changing how the model thinks about the Holodomor is completely irrelevant.

	▲	BoorishBears 23 minutes ago \| parent [-]
		> Changing how the model thinks about the Holodomor is completely irrelevant. Your post title is literally "Distilling DeepSeek into GPT-OSS doesn't transfer censorship." Like I'm not really interested in debating you on this because even the title is nonsense, there is no good faith interpretation of what you're doing here. Distillation is such a wide concept, and you have such a narrow domain, it's not an even somewhat useful experiment to make the claim that you're making.