News for hackers. Stuff that matters.

A comment on DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL.

[dead]
Re:DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Sc... by mluo on Tuesday February 11, 2025 @04:27PM (#43018592)
One of the authors here....

This is not a Chinese model, btw I'm American

[ Parent | on HN ]
Re:DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Sc... by NotYourLawyer on Tuesday February 11, 2025 @04:55PM (#43018856)
Oh sorry, I skimmed and thought this was based on Deepseek R1.
[ Parent | on HN ]
Re:DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Sc... by nicce on Tuesday February 11, 2025 @04:24PM (#43018556)
Distilled models always knew. Not sure about the full model since it is hard to run by myself.
[ Parent | on HN ]