logoalt Hacker News

alightsoul • yesterday at 6:49 PM • 2 replies • view on HN

Maybe have A second model do the management?


Replies

theroadnotbacon • yesterday at 6:54 PM

Looks like they tested that in the paper, and the code allows for it as well. https://github.com/facebookresearch/context-language-models/... Of course, this is for suggesting context management strategies rather than the actual management afaict.

➕ show 1 reply
vatsachak • yesterday at 9:37 PM

Yeah, that would be the canonical solution. Modularity is better