Hacker News new | ask | show | jobs
user: mluo
created: 2023-01-24
karma: 51

submissions:

0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
0 points | 0 comments
DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL
19 points | 0 comments
0 points | 0 comments
0 points | 0 comments