Re:A global workspace in language models
by unleaded on Monday July 06, 2026 @07:00PM
(#48811593)
I don't think it's solved this fundamental architectural problem by itself, it will have just squeezed the edge cases thinner. It keeps happening, people find a question it gets stupidly wrong, the vendors proclaim they've fixed it, then another one gets found.
[ Parent
| on HN ]
There are no comments on this comment yet.