This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Dmitrii Krasheninnikov
Posts
Sorted by New
7
A Sober Look at Steering Vectors for LLMs
7h
0
1
Dima's Shortform
3mo
0
Wiki Contributions
Comments
Sorted by
Newest
Meta learning to gradient hack
Dmitrii Krasheninnikov
2y
2
0
Could you please share the results in case you ended up finishing those experiments?
Reply
Could you please share the results in case you ended up finishing those experiments?