AI Dynamics

Global AI News Aggregator

Adversarial Policies Exploit Weaknesses in Superhuman Go AIs

Adversarial Policies Beat Superhuman Go AIs Their policies do not win by playing Go well. Instead, they trick AI into making serious blunders! These tricks transfer to other superhuman Go AIs and can be used by humans to consistently beat superhuman AIs. https://
arxiv.org/abs/2211.00241

→ View original post on X — @hardmaru,

Commentaires

Leave a Reply

Your email address will not be published.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