undefined | Better HN

0 pointsmetalliqaz2mo ago0 comments

The discussion is about training an LLM on old text and then asking it about new concepts.

0 comments

AlphaGo was trained on old games and then presented with a game it had never seen before. It came up with a move that a human would not have played.

j / k navigate · click thread line to collapse

0 pointsmetalliqaz2mo ago0 comments

The discussion is about training an LLM on old text and then asking it about new concepts.

djwide2mo ago

AlphaGo was trained on old games and then presented with a game it had never seen before. It came up with a move that a human would not have played.

j / k navigate · click thread line to collapse