I Am Going To Hit AI With A Hammer And See What Happens
Seeds of Science
SubscribeSign in
The Best of Science Blogging<br>I Am Going To Hit AI With A Hammer And See What Happens<br>If you want your AI to be more embedded in the real world you will probably have to pay for it with vulnerability (author: Peter Curry)
Seeds of Science<br>Aug 05, 2026
10
Share
Peter Curry blogs about neuroscience and related subjects at King Canute. His current interests are in the intersection of artificial intelligence and neuroscience, and his MSc in Cognitive Neuroscience focused on predictive processing and active inference. He also has a history degree, writes comedy, and produces dance music. He lives in London.<br>This Substack is reader-supported. To receive new posts and support my work, consider becoming a free or paid subscriber.
Subscribe
The Game of Chess
The Game of Chess, Sofonisba Anguissola, c. 1555.<br>I love speed chess. It’s a completely different game to normal, classical chess, where you have many minutes to think about a move. In speed chess, you have a few seconds to make any given move, and you are balancing two metrics.<br>The first is how well you are doing on the board. The second is how well you are doing on time. You might be playing a hopeless position, but your opponent has five seconds left, and you have a minute. You can sacrifice some pieces without any real intent, force your opponent to think, and run them out of time.<br>If you ever watch chess hustler videos, this is often what they’re doing. Hustlers are strong chess players who want to take you out of your comfort zone. They will play weird trick openings that are not theoretically optimal, but contain many traps for unsuspecting players.<br>I’ve played against these openings many times, and they are horrible to play against. Nothing but traps, one after another.<br>The way I learned to deal with those multi-trap openings is to fall into them, find out how to avoid it, and then to fall into the next one.<br>Every chess grandmaster is incredibly strong at speed chess. This is because they’ve done the process I just described, but for many more openings. There aren’t many of those weird positions that they don’t know. They’ve spent enough time playing chess that they aren’t going to get bamboozled by a hustler.<br>But most chess players will.<br>The Game of Go
In chess, there are six different pieces, with different functions. The differences between them are simple, in that they move in different ways. But they are also complex, in that they create striking patterns.<br>Demis Hassabis famously wooed Peter Thiel by telling him that “the bishop and knight are worth three points each but have such different powers. All the creative tension comes when you swap the bishop for the knight in certain positions.” (The things that woo billionaires are different to those that work on us mere mortals.)<br>In the game of Go, there is one piece. It’s a stone. The board is larger, and the complexity comes from trying to understand the way that this singular piece interacts with many others across a large board.<br>You may have heard of AlphaGo and AlphaZero (a more advanced version of AlphaGo). These are dominant Go-playing engines, and they are created by reinforcement learning. These engines play thousands of games against themselves, using the outcomes to figure out which moves were likely to lead to victory. AlphaGo famously beat Lee Sedol, one of the best players in the world, over five games.1<br>Recently, a Go engine named KataGo has emerged. It is a strong engine that can beat highly-ranked human players. In 2022, a team found an adversarial strategy that beats KataGo, but loses to Go amateurs. Since Kata backwards is Atak, I’m going to call this general class of strategies AtakGo.<br>Gleave explains that, during a Go match, the adversarial policy works by first staking claim to a small corner of the board. He provided a link to an example in which the adversary, controlling the black stones, plays largely in the top-right of the board. The adversary allows KataGo (playing white) to lay claim to the rest of the board, while the adversary plays a few easy-to-capture stones in that territory.
An example of a KataGo versus adversary board state. In Go, you want to control territory, and as you can see, white has a lot more territory, with just a few black stones that can be easily captured.<br>“This tricks KataGo into thinking it’s already won,” Gleave says, “since its territory (bottom-left) is much larger than the adversary’s. But the bottom-left territory doesn’t actually contribute to its score (only the white stones it has played) because of the presence of black stones there, meaning it’s not fully secured.”<br>As a result of its overconfidence in a win—assuming it will win if the game ends and the points are tallied—KataGo plays a pass move, allowing the adversary to intentionally pass as well, ending the game. (Two consecutive passes end the game in Go.) After that, a point tally...