x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Mia Hopman — LessWrong
Mia Hopman
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
17
Current LLM agents need strong pressure to engage in scheming behavior
16d
0
39
Prompt optimization can enable AI control research
2mo
4
51
Optimally Combining Probe Monitors and Black Box Monitors
Ω
4mo
Ω
2
30
Untrusted AIs can exploit feedback in control protocols
6mo
0
Comments