AI Dynamics

Global AI News Aggregator

Self-examination in AI science models for error detection

what would be cool with science models like Galactica would be to add self examination of the inputs like the coming Codex model, where the model can inspect it’s theorem proofs or essays and spot errors

→ View original post on X — @thom_wolf,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *