Re:Adversarial Policies Beat Professional-Level Go AIs
by EchoAce on Thursday November 03, 2022 @06:04PM
(#33458465)
As a Go player myself, I agree that Go-wise this result isn't impressive. But isn't the point that it's an "attack" on the AI? Like for password leaks, failed hash functions, etc, we don't care that it's 100% broken, just that there are tiny artifacts that can be exploited.
[ Parent
| on HN ]
There are no comments on this comment yet.