logoalt Hacker News

imtringued • today at 1:03 PM • 1 reply • view on HN

I don't get it. Weights don't change means the model can't learn.

This is not merely an implementation detail, continual learning is the core of AGI.


Replies

brainwad • today at 1:42 PM

It means the weights by themselves can't learn. But they could be used in a harness that can learn in other ways. Insisting that it be done at the neural net level seems anthropocentric - because we form memories via neural connections, that everything else must, too.

Also: I wouldn't say a human with amnesia who relied on notes to their future selves lacks intelligence, so I'm not sure being able to form memories is in fact necessary.

➕ show 1 reply