dmm: (Default)
Dataflow matrix machines (by Anhinga anhinga) ([personal profile] dmm) wrote 2023-02-05 06:29 am (UTC)

This is a Feb 3 interview.

Neel Nanda solved the mystery of "Grokking" as an independent researcher.

Before that he co-authored other cool papers about internal mechanisms of Transformer-based models while at Anthropic AI.

Post a comment in response:

This account has disabled anonymous posting.
If you don't have an account you can create one now.
HTML doesn't work in the subject.
More info about formatting