HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
1.
▲
Launch HN: RunRL (YC X25) – Reinforcement learning as a service
runrl.com
22 comments
9 months ago
ag8
71 points
2.
▲
Training Qwen to answer briefly yet intelligently using feedback control
runrl.com
discuss
9 months ago
ag8
4 points
3.
▲
Why Run RL? How specialized models can outperform the biggest LLMs
runrl.com
discuss
a year ago
-_-
4 points
4.
▲
Scaling pretraining affects RL sample efficiency
runrl.com
discuss
8 months ago
ag8
1 points
5.
▲
Generating the Funniest Joke with RL
runrl.com
discuss
a year ago
ag8
1 points