Statistics
Publications
4
Citations
83
H-Index
4
Active since
2007
Affiliations
University of Oxford(Current)
Monte MacDiarmid is an author at University of Oxford specializing in computer science, engineering, and aircraft aerodynamics testing.
Publications per year
2007–2024
4
4
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Evan Hubinger, Carson Denison, Jesse Mu et al. · arXiv (Cornell University) · 2024 · 34 citations · Full text
Alignment faking in large language models
Ryan Greenblatt, Carson Denison, Benjamin Fletcher Wright et al. · arXiv (Cornell University) · 2024 · 20 citations · Full text
1–4 of 4