Skip navigation
Demis confirmed DeepMind hasn’t cracked continual learning.
0:00 / 1:27

Demis confirmed DeepMind hasn’t cracked continual learning.

Yuchen Jin

@Yuchenj_UW92K followers

Visit on X
775 likesDownloadOriginal post

75,633 views

Demis confirmed DeepMind hasn’t cracked continual learning. There were rumors on X that Google DeepMind had solved it. Not true. They’re experimenting with blending AlphaZero with large foundation models to see if it can scale and generalize to the real world, not just games.

Comments

Comments from the original post on X (Twitter)

No comments yet