I'm trying to figure out whether this is a fair (and, I hope, neutral) representation of what the authors have achieved here:
The result of training Othello-GPT is a program which, on being fed a string conforming to the syntax used to represent moves in an Othello game, outputs a usually-valid next move.
Through their probing of this program, the authors have gained an understanding of the program's state after processing the input. This state can also be interpreted as representing the state of the board in the game represented by the input string.
This understanding allows them to make predictions about what state they would expect the program to be in if the board had reached a slightly different state (in the examples given, the changes are flips of a single disc, without regard to whether this state of play could be reached through valid moves.)
When the state of the program is modified to match the predicted state, it goes on to produce a move which is usually valid for the new board state.
The result of training Othello-GPT is a program which, on being fed a string conforming to the syntax used to represent moves in an Othello game, outputs a usually-valid next move.
Through their probing of this program, the authors have gained an understanding of the program's state after processing the input. This state can also be interpreted as representing the state of the board in the game represented by the input string.
This understanding allows them to make predictions about what state they would expect the program to be in if the board had reached a slightly different state (in the examples given, the changes are flips of a single disc, without regard to whether this state of play could be reached through valid moves.)
When the state of the program is modified to match the predicted state, it goes on to produce a move which is usually valid for the new board state.