Sai Krishna Gottipati
TalkRL: The Reinforcement Learning Podcast
00:00
What Do You Think About Explainability in Chess?
I wonder what you think about explainability in terms of ches a i. Like, do you think we could ever get to the point where we could have a discussion with the ches ai about strategy? Or is that kind of a ridiculous concept? I think it can explain why it thinks, why it thinks a particular move is good, but that explanation would still be based on the variations that it's calculating and not in any like natural language That wouldn't happen anytime soon though. We need a lot of novel data to train such morelsbut which are not easily accessible or within a reasonable amount of compute. It's a very tough challenger.
Play episode from 01:03:16
Transcript
