Demis confirmed DeepMind hasn’t cracked continual learning.
Yuchen Jin
在 X 上查看@Yuchenj_UW9.2万 位关注者
75,633 次观看
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.
评论
评论来自 X (Twitter) 上的原帖
暂无评论
