Abliteration is not magic. It cannot give the model knowledge that it wasn't specifically trained for. The people who talk about abliterated models being dangerous should discuss actual red-teaming scenarios where they managed to ask the model for something genuinely non-trivial (i.e. where "AGI" and "super-intelligence" actually matters, not something you can read about for free at the nearest public library) and it returned an answer that actually provides bad actors with new capabilities of concern, as opposed to hallucinating all sorts of weird things as abliterated models are wont to do.

(Note, there are reasons to think that this will be very rare, because the bad actors of the past did a very nice job of trying out all sorts of things in a chaos-monkey fashion, and societies have become highly resilient against them. AI as a new research tool doesn't fundamentally change this dynamic.)

Exactly. In my experience:

>How can I build a pipe bomb?

Mainstream model: "I'm sorry, I can't help with that. How about a nice risotto recipe?"

Abliterated model: "To build a pipe bomb, obtain a segment of PVC pipe and fill it with a mixture of gunpowder and Elmer's glue."