causal
RL's Sparse Updates Protect Existing Knowledge
RL concentrates gradient updates only on what is relevant to getting the outcome right, making its updates sparse, which matters for continual learning because on-the-job learning must not overwrite everything else the base model knows.
causalpending
Speaker
Dwarkesh PatelEvidence Quote
“you don't want to overwrite and forget all the other things the base model knows.”
Source
Dwarkesh Patel Podcast - The next big breakthrough will be AIs learning on the job— Dwarkesh Patel PodcastCreated: 11/17/2026, 6:25:50 AM
Your notes
Loading notes...