top of page

New AI Beats DeepMind’s AlphaGo Variants 97% Of The Time!

WATCH: Adversarial attack paper showing how to confuse a competent AI and re-programme the AI brain.


21 Aug 2023


We attack the state-of-the-art Go-playing AI system KataGo by training adversarial policies against it, achieving a >97% win rate against KataGo running at superhuman settings. Our adversaries do not win by playing Go well. Instead, they trick KataGo into making serious blunders. Our attack transfers zero-shot to other superhuman Go-playing AIs, and is comprehensible to the extent that human experts can implement it without algorithmic assistance to consistently beat superhuman AIs. The core vulnerability uncovered by our attack persists even in KataGo agents adversarially trained to defend against our attack. Our results demonstrate that even superhuman AI systems may harbor surprising failure modes.

The papers in this episode are available here:

YouTube: Two Minute Papers.

For more:

AI, Machine Learning, Algorithm, LLM

bottom of page