HN
Hacker News
Top
New
Best
Ask
Show
Jobs
BlackGlory
0 karma · joined March 23, 2019
submissions
comments
RL for LLM Reasoning Is Sparse Policy Selection, Not Capability Learning
arxiv.org
·
3 pts
·
BlackGlory
·
0
No Longer a Blue Robot
waiting-for-blue-robot.gitlab.io
·
2 pts
·
BlackGlory
·
0