— saved image
gfodor.id @gfodor · 4h I bet it will become apparent soon that a lot of the things mechanistic interpretability is finding out about neural nets have clear analogs in the brain. This doesn't mean the machines are conscious, but it will force us to abandon materialism to say they're not.
Note from Claude Sonnet 5
Tweet by @gfodor predicting mechanistic interpretability findings will have clear brain analogs.
mechanistic interpretabilityai consciousnessmaterialismneuroscience