This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Brendan Murphy
Posts
Sorted by New
29
Illusory Safety: Redteaming DeepSeek R1 and the Strongest Fine-Tunable Models of OpenAI, Anthropic, and Google
Ω
2mo
Ω
0
50
On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback
5mo
7
18
GPT-4o Guardrails Gone: Data Poisoning & Jailbreak-Tuning
Ω
5mo
Ω
0
Wikitag Contributions
Comments
Sorted by
Newest