This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
is fundraising!
LW
$
Login
Brendan Murphy
Posts
Sorted by New
47
On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback
1mo
6
18
GPT-4o Guardrails Gone: Data Poisoning & Jailbreak-Tuning
Ω
2mo
Ω
0
Wiki Contributions
Comments
Sorted by
Newest