Real-time AI hallucination detection with timeplus: A chess example

So you have to be able to identify a priori what is and isn't an hallucination right?

I didn’t understand quite the point of the claims from end of the page. Surely automatic cars or health/banking services don’t use language models for anything important. Everyone knows those hallucinate. ML is lot better alternative.

There’s a more generalizable work on this recently for those expecting more. https://github.com/leochlon/hallbayes

is this satire?

[dead]