Re:‘The Godfather of A.I.’ Leaves Google and Warns of Danger...
by robertlagrant on Tuesday May 02, 2023 @04:40AM
(#35784847)
This sounds to my inexpert ear like a great summary.
The only thing I'd query is whether it would be possible to isolate text that tries to modify the LLM's behaviour (e.g. DAN). I don't really understand the training process that led to that behaviour, and so to my mind it's still worth exploring whether it can be stopped.
The only thing I'd query is whether it would be possible to isolate text that tries to modify the LLM's behaviour (e.g. DAN). I don't really understand the training process that led to that behaviour, and so to my mind it's still worth exploring whether it can be stopped.