Interesting, and impressive to just whip up a new learning architecture single handedly like this ! There was a paper on how to inject memory into the last layer(s) of a normal transformer architecture. Seemed a bit 'hacky' but not sure which is better. No matter, In a few months we'll have several architectures and techniques to choose from, that all replace/augment primitive RAG systems, so the missing parts of the artificial brain is being developed everywhere.
post
there doesn't seem to be anything here
2 comments in c/artificial_intel@lemmy.ml view that post
replies:
no comments (yet)