Comment on Judges Are Fed up With Lawyers Using AI That Hallucinate Court Cases
Moose@moose.best 4 weeks agoI don’t know if I would call it lying per-se, but yes I have seen instances of AI’s being told not to use a specific tool and them using them anyways, Neuro-sama comes to mind. I think in those cases it is mostly the front end agreeing not to lie (as that is what it determines the operator would want to hear) but having no means to actually control the other functions going on.
webghost0101@sopuli.xyz 4 weeks ago
Neurosama is a fun example but we dont really know the sauce vedal coocked up.
When i say proven i mean 32 page research paper specifically looking into it.
arxiv.org/abs/2407.12831
They found that even a model trained specifically on honesty will lie if it has an incentive.