Join Nostr
2026-10-16 15:39:41 UTC
in reply to

Ted Underwood on Nostr: "mechanistic interpretability" in particular. Mapping neurons might get old. We might ...

"mechanistic interpretability" in particular. Mapping neurons might get old. We might decide that the interesting questions are about (say) the architectures that shape communication flow between groups of agents. Or something!

This is not exactly a new thought, but when it's occurred to me