I think i’ve only once flat out told one it was wrong about a specific assertion I quoted and it immediately was able to find its way to what I knew to be the correct claim.
I just wonder what would happen if i was in fact mistaken and I told it confidently it was wrong without elaborating
Yeah you gotta specifically prompt for that in great detail though.
The only consistent way I’ve gotten ai disagreement is as part of an agent or harness or with some moe models.