News for hackers. Stuff that matters.
Re:The Emergent Symbolic Structure of Artificial Neural Netw... by eli_gottlieb on Wednesday September 02, 2026 @10:11AM (#49536539)
> So at least some of what LLMs do internally seems to involve a bit more structure than just linear combinations of some overcomplete dictionary.

Well that's good to hear. Would have been rather exasperating to find out we could have somehow gotten Fable or Sol out of sufficiently advanced sparse-coding ages ago.

There are no comments on this comment yet.