Javascript is not enabled. This site can still works but it'll be more interactive when javascript is enabled.
loading...
Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
piratebroadcast
4 hours ago
|
on: Show HN: I RL-trained an agent that trains models with RL (for ~$1.3k)
To circumvent distillation.
reply
Hacker News new | past | comments | ask | show | jobs | submit