x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
is fundraising!
LW
Login
Robert Kirk — LessWrong
Robert Kirk
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
17
Appendices: Supervised finetuning on low-harm reward hacking generalises to high-harm reward hacking
6d
0
14
Supervised finetuning on low-harm reward hacking generalises to high-harm reward hacking
Ω
6d
Ω
0
13
Layered AI Defenses Have Holes: Vulnerabilities and Key Recommendations
Ω
6mo
Ω
1
Comments