[testartr]

and models are still pretty bad at playing tic-tac-toe, they can do it, but think way too much

it's easy to focus on what they can't do

[big-and-small]

Everything is about context. When you just ask non-concrete task it's still have to parse your input and figure what is tic-tac-toe in this context and what exactly you expect it to do. This is why all "thinking".

Ask it to implement tic-tac-toe in Python for command line. Or even just bring your own tic-tac toe code.

Then make it imagine playing against you and it's gonna be fast and reliable.

[testartr]

prompt was very concrete: draw a tic tac toe ASCII table and let's play. gemini 2.5 thought for pages particular moves