News for hackers. Stuff that matters.
Re:Even 'uncensored' models can't say what they want by CamperBob2 on Monday April 20, 2026 @07:53PM (#47842766)
Because AI is not intelligent, it doesn't "know" what it previously output even a token ago.

You have no idea what you're talking about. I mean, literally no idea, if you truly believe that.

Re:Even 'uncensored' models can't say what they want by codebje on Monday April 20, 2026 @08:40PM (#47843157)
That's only true if you consider the process the LLM is undergoing to be a faithful replica of the processes in the brain, right?
Re:Even 'uncensored' models can't say what they want by CamperBob2 on Monday April 20, 2026 @09:02PM (#47843309)
No.