I am looking forward to models that have post-training on selectively compacting their own context - so they can choose what to forget and what to edit. That alone would make coding agents multiple times more powerful on large code bases.

From Twitter
Disclaimer: The content above is only the author's opinion which does not represent any position of Followin, and is not intended as, and shall not be understood or construed as, investment advice from Followin.
Like
Add to Favorites
Comments