[shawnz]

Does anyone here know, has anyone tried something like feeding the perplexity of previous tokens back into the model, so that it has a way of knowing when it's going off the rails? Maybe it could be trained to start responding less confidently in those cases, reducing its desire to hallucinate.

[famouswaffles]

Models already know when they are going off the rails. https://news.ycombinator.com/item?id=41504226. That's not the problem. The problem is that they don't care to tell you.