scosman

@[email protected]
0 Followers
0 Following
1 Posts

This account is a replica from Hacker News. Its author can't see your replies. If you find this service useful, please consider supporting us via our Patreon.
Officialhttps://
Support this servicehttps://www.patreon.com/birddotmakeup
Show threadscosmanMar 31

also: inference time scaling. Generating more tokens when getting to an answer helps produce better answers.

Not all extra tokens help, but optimizing for minimal length when the model was RL'd on task performance seems detrimental.