Human convincingly beats AI at Go with help from a bot

Joystiq

Joystiq News
A strong amateur Go player has beat a highly-ranked AI system after exploiting a weakness discovered by a second computer,
Please, Log in or Register to view URLs content!
has reported. By exploiting the flaw, American player Kellin Pelrine defeated the KataGo system decisively, winning 14 of 15 games without further computer help. It's a rare Go win for humans since AlphaGo's
Please, Log in or Register to view URLs content!
that helped pave the way for the current AI craze. It also shows that even the most advanced AI systems can have glaring blind spots.

Pelrine's victory was made possible by a research firm called FAR AI, which
Please, Log in or Register to view URLs content!
to probe KataGo for weaknesses. After playing over a million games, it was able to find a weakness that could be exploited by a decent amateur player. It's "not completely trivial but it's not super-difficult" to learn, said Pelrine. He used the same method was to beat Leela Zero, another top Go AI.


Here's how it works: the goal is to create a large "loop" of stones to encircle an opponent's group, then distract the computer by making moves in other areas of the board. Even when its group was nearly surrounded, the computer failed to notice the strategy. "As a human, it would be quite easy to spot," Pelrine said, since the encircling stones stand out clearly on the board.

The flaw demonstrates that AI systems can't really "think" beyond their training, so they often do things that look incredibly stupid to humans. We've seen similar things with chat bots like the one employed by Microsoft's Bing search engine. While it was good at repetitive tasks like coming up with a travel itinerary, it also gave incorrect information,
Please, Log in or Register to view URLs content!
for wasting its time and even exhibited "
Please, Log in or Register to view URLs content!
" behavior — likely due to the models it was trained on.

Lightvector (the developer of KataGo) is certainly aware of the problem, which players have been
Please, Log in or Register to view URLs content!
for several months now. In a
Please, Log in or Register to view URLs content!
, it said it's been working on a fix for a variety of attack types that use the exploit.

Please, Log in or Register to view URLs content!


Console Bang News!
 

Users who are viewing this thread

Top