alt Hacker News> Calling the second system a “next-move predictor” would be strange. It is not trying to predict what move appeared next in a dataset. It is trying to choose a move that wins.
i dont understand the distinction here. does working backwards from a set of win states instead of working forwards from the current state somehow change whether it’s a prediction or not?
Replies
danielmarkbruce • today at 7:54 PM
The word "predict" has a meaning. I don't "predict" my next move in chess. I might predict what someone elses first move is.
➕ show 3 replies
The distinction is that it's not 'predicting the next token'. Instead it's _determining_ the next token based on a prediction of its reward signal.