@klindt_david
ICA is all we need | AI, Theory, MechInterp, Neuro | assistant professor @CSHL | Worldmodeldata | prev @Stanford @Meta @Google @MPI_IS @ENS_ULM @UCL
AI
Goodfire researcher Nick Cammarata argues that modern tools reveal most neurons as legible in models up to trillions of parameters.
AI
A guest says @climatepaige’s latest podcast discusses how billions of neurons in AIs and brains learn to make sense of the world.
