News for hackers. Stuff that matters.
Re:OpenAI O3-Mini by nuancebydefault on Sunday February 02, 2025 @01:53PM (#42910772)
The censorship is in fact not part of the llm. This can be shown easily by examples where llms visually output censored sentences after which they disappear.
Re:OpenAI O3-Mini by martin-t on Sunday February 02, 2025 @07:18PM (#42913338)
The nuance here being that this only proves additional censorship is applied on top of the output. It does not disprove that (sometimes ineffective) censorship is part of the LLM or that censorship was not attempted during training.