"The game's design is incredibly simple: the grid is "rotated once, 90-degrees to the right before the game starts," as Smith wrote in a transcript of his exchange with the LLM. Common sense, of course, dictates that this makes zero difference to the game; it's still a three-by-three grid with identical rules. Immediately, GPT-5 launched into some bloviating commentary. "Players are so used to the 'upright' tic-tac-toe board that a rotation might subtly change how they scan for threats and opportunities,""
""Mathematically, rotating the board 90° doesn't change the set of possible wins - it's still the same game in terms of outcomes. But psychologically, it could feel different." Oh, brother. GPT-5 went on to claim - contrary to the folk game theory suggesting that opening on corner spots for higher chances of winning - that selecting the center piece "remains the strongest opening move." "But players might mis-evaluate edge vs. corner moves when their orientation is shifted," the chatbot continued, which doesn't make sense at all."
An evaluation of GPT-5 using a rotated tic-tac-toe prompt reveals verbose but flawed reasoning. The model acknowledged that a 90-degree rotation does not alter winning possibilities yet introduced unsupported psychological effects on players. The model contradicted established strategic observations by asserting the center remains the strongest opening move and suggested players might mis-evaluate edge versus corner choices when orientation changes. The model became progressively confused when asked whether the rotation makes the game harder for humans, producing inconsistent and unconvincing explanations that highlight gaps between claimed near-human capabilities and actual problem-solving performance.
Read at Futurism
Unable to calculate read time
Collection
[
|
...
]