News for hackers. Stuff that matters.
Re:ChatGPT Has Gone Berserk by AnarchismIsCool on Wednesday February 21, 2024 @05:04PM (#39460288)
Sure, but it's still a statistical model, it doesn't know what the instructions mean, it just does what those instructions statistically link to in the training data. It's not doing perfect forward logic and never will in this paradigm.
Re:ChatGPT Has Gone Berserk by astrange on Wednesday February 21, 2024 @05:31PM (#39460539)
The fine tuning process isn't itself a statistical model, so that principle doesn't work on it. You beat the model into shape until it does what you want (DPO and varieties of that) and you can test that it's doing that.
Re:ChatGPT Has Gone Berserk by AnarchismIsCool on Wednesday February 21, 2024 @06:14PM (#39460984)
Yeah but you're still beating up a statistical model that's gonna do statistical things.

Also we're talking about prompt engineering more than fine-tune