Re:Man beats machine at Go in human victory over AI
by gwern on Saturday February 18, 2023 @11:12AM
(#34847966)
Yeah, it seems unlikely that some patchup can fix, in generality, such a deep blindspot. It reminds me of the problems AlphaGo had with ladders: I'm not sure DM ever really solved the ladder blindness, it just got good enough that they became irrelevant in practice.
We're looking into doing our own adversarial training run to see if we can get to a point where the KataGo agent is robust. My personal suspicion given how difficult adversarial examples have been to eliminate in image classifiers and other ML systems is that although we'll be able to train particular vulnerabilities out of the system, there's still going to be a long tail of issues that can be automatically discovered and exploited.