News for hackers. Stuff that matters.
Re:Show HN: Distilling DeepSeek into GPT-OSS doesn't transfe... by dluan on Thursday July 30, 2026 @03:50PM (#49114868)
It'd be interesting to use this technique to create a running tally across all models of which models are censored on what topics
Re:Show HN: Distilling DeepSeek into GPT-OSS doesn't transfe... by jubilee33 on Thursday July 30, 2026 @04:29PM (#49115331)
Yes but in which jurisdiction could you publish it? We roughly know what the hot topics are for the current models, but actually testing and ranking would break said censorship and thus would be hammered into the ground through cointelpro methods by all parties.

It would be nice to have a hypothetical small country where the internal censorship would be non aligned and insignificant enough that it wouldn't take away from the overall findings. But it doesn't exist.

I want some science based authority on the moon where only 3-sigma IQ international academics have ultimate authority. Oh wait Asimov did that right? I guess it didn't go so well either.

More important there are some things censored that are true. And some things censored that are false. How do we even get to a good model of the truthiness/nonsense adjustment indicator?

Re:Show HN: Distilling DeepSeek into GPT-OSS doesn't transfe... by vessenes on Thursday July 30, 2026 @05:33PM (#49116107)
You could publish this in the US easily. 145 IQ peeps get tons of stuff wrong, btw, and in many domains my experience is the ‘wrongness’ can intensify as you move up into higher sigma domains.
Re:Show HN: Distilling DeepSeek into GPT-OSS doesn't transfe... by cgorlla on Thursday July 30, 2026 @04:41PM (#49115476)
Agreed, we find this to be an interesting reflection of societal values and norms inasmuch LLMs are.
Re:Show HN: Distilling DeepSeek into GPT-OSS doesn't transfe... by culi on Thursday July 30, 2026 @06:13PM (#49116553)
A "free speech" benchmark already exists https://speechmap.ai/labs/