Comment by anvuong
20 hours ago
Not really. The gpt-oss models were notoriously hard to remove the built in safety. It totally depends how it was trained.
20 hours ago
Not really. The gpt-oss models were notoriously hard to remove the built in safety. It totally depends how it was trained.
Also from the recent Kimi models it seems that it was difficult to remove the censorship.
But in both cases, eventually uncensored variants were published, even if it took more time than for other models.