An interesting adversarial attack at KataGo, a professional level Go AI. Apparently funded by Fund for Alignment Research (FAR). Seems to be a good use of fund.
Note that when given additional search, KataGo realizes that it will lose here and doesn't fall for the attack, which seems to suggest that it's not just a rules discrepancy.
An interesting adversarial attack at KataGo, a professional level Go AI. Apparently funded by Fund for Alignment Research (FAR). Seems to be a good use of fund.