News for hackers. Stuff that matters.

A comment on Our Smallest, Most Efficient Model: Muse Ember. Parent comment

Re:Our Smallest, Most Efficient Model: Muse Ember by valzam on Tuesday November 10, 2026 @04:20AM (#50437886)
It feels like an antipattern to add so many reasoning levels as options. How am I as user reasonably going to choose between them?
[ Parent | on HN ]
Re:Our Smallest, Most Efficient Model: Muse Ember by WhyNotHugo on Tuesday November 10, 2026 @05:15AM (#50438235)
You use a decider model which reads your prompt and picks the right reasoning level.
[ Parent | on HN ]
Re:Our Smallest, Most Efficient Model: Muse Ember by InsideOutSanta on Tuesday November 10, 2026 @05:31AM (#50438371)
But which effort level should I use for the decider model?

(I think there's at least some evidence that it is difficult for decider models to predict the complexity of a task ahead of time with any level of reliability.)

[ Parent | on HN ]