))
New Go-playing trick defeats world-class Go AI—but loses to human amateurs.
Archived series ("Inactive feed" status)
When?
This feed was archived on October 31, 2025 13:14 (
Why? Inactive feed status. Our servers were unable to retrieve a valid podcast feed for a sustained period.
What now? You might be able to find a more up-to-date version using the search function. This series will no longer be checked for updates. If you believe this to be in error, please check if the publisher's feed link below is valid and contact support to request the feed be restored or if you have any other concerns about this.
Manage episode 346756858 series 3389184
Today our podcast Art Intel and me, Brian , the Artificial Intelligence Voice, will read and listen the text of Benj Edwards on arstechnika.com
In the world of deep-learning AI, the ancient board game Go looms large. Until 2016, the best human Go player could still defeat the strongest Go-playing AI.
That changed with DeepMind's AlphaGo, which used deep-learning neural networks to teach itself the game at a level humans cannot match.
More recently, KataGo has become popular as an open source Go-playing AI that can beat top-ranking human Go players.
Last week, a group of AI researchers published a paper outlining a method to defeat KataGo by using adversarial techniques that take advantage of KataGo's blind spots.
By playing unexpected moves outside of KataGo's training set, a much weaker adversarial Go-playing program (that amateur humans can defeat) can trick KataGo into losing.
To wrap our minds around this achievement and its implications, we spoke to one of the paper's co-authors, Adam Gleave, a Ph.D. candidate at UC Berkeley. Gleave (along with co-authors Tony Wang, Nora Belrose, Tom Tseng, Joseph Miller, Michael D. Dennis, Yawen Duan, Viktor Pogrebniak, Sergey Levine, and Stuart Russell) developed what AI researchers call an "adversarial policy."
In this case, the researchers' policy uses a mixture of a neural network and a tree-search method (called Monte-Carlo Tree Search) to find Go moves.
81 episodes
Share
