[SkiFire13]

I don't see Tao claiming ChatGPT proved a theorem. Moreover most questions seemed to be about something already talked about online, so it seems plausible that it was included in the training data. This is IMO a big issue with evaluating LLMs, you can't keep asking the same questions because you can't be sure they will eventually answer by memory or actually reason.

[tonyhart7]

"or actually reason." how can you be sure it actually do "reasoning" ??? all I can see just made up some nonsense words

[SkiFire13]

That's the point of my comment though...