Mia Hopman

Karma: 152

Understanding when and why agents scheme

Mia Hopman, Jannes Elstner, Maria Avramidou, Amritanshu Prasad and David Lindner

21 Mar 2026 20:33 UTC

37 points

0 comments4 min readLW link

Current LLM agents need strong pressure to engage in scheming behavior

Mia Hopman, Jannes Elstner, Maria Avramidou, Amritanshu Prasad, David Lindner and LASR Labs

20 Nov 2025 20:45 UTC

23 points

0 comments11 min readLW link

Prompt optimization can enable AI control research

Mia Hopman and ZachParent

23 Sep 2025 12:46 UTC

40 points

4 comments9 min readLW link

Optimally Combining Probe Monitors and Black Box Monitors

Tim Hua, James Baskerville, BionicD0LPH1N, Mia Hopman, Aryan Bhatt and Tyler Tracy

27 Jul 2025 19:13 UTC

52 points

2 comments6 min readLW link

Untrusted AIs can exploit feedback in control protocols

Mia Hopman, BionicD0LPH1N and Tyler Tracy

27 May 2025 16:41 UTC

30 points

0 comments16 min readLW link