x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Joschka Braun — LessWrong
Joschka Braun
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
17
Exploration hacking: can reasoning models subvert RL?
Ω
5mo
Ω
4
40
A Sober Look at Steering Vectors for LLMs
Ω
1y
Ω
0
Comments