Asa Cooper Stickland

Asa Cooper Stickland

I'm a research scientist at the UK AI Security Institute, working on AI control and model organisms of misalignment. I was previously a postdoc with Sam Bowman at NYU, did MATS with Owain Evans, and mentored for the MATS, SPAR and Pivotal fellowships. I got my PhD at the University of Edinburgh, supervised by Iain Murray.

Publications

Highlighted Research

Async Control: Stress-testing Asynchronous Control Measures for LLM Agents
Asa Cooper Stickland, Jan Michelfeit, Arathi Mani, Charlie Griffin, Ollie Matthews, Tomek Korbak, Rogan Inglis, Oliver Makins, Alan Cooney (2025)
We conducted a red-blue team game in realistic SWE environments, where the red team designed agents to sabotage, and the blue team designed monitors to catch the agent.
ControlArena
Ollie Matthews, Rogan Inglis, Tyler Tracey, Oliver Makins, Tom Catling, Asa Cooper Stickland, Rasmus Faber-Espensen, Daniel O’Connell, Myles Heller, Miguel Brandao, Adam Hanson, Arathi Mani, Tomek Korbak, Jan Michelfeit, Dishank Bansal, Tomas Bark, Chris Canal, Charlie Griffin, Jasmine Wang, and Alan Cooney. (2025)
Software for running AI control experiments.
Future events as backdoor triggers: Investigating temporal vulnerabilities in LLMs
Sara Price, Arjun Panickssery, Sam Bowman, Asa Cooper Stickland (2024)
Language models can trigger backdoors only on future events (allowing them to only trigger during deployment).
Taken out of context: On measuring situational awareness in LLMs
Lukas Berglund*, Asa Cooper Stickland*, Mikita Balesni*, Max Kaufmann*, Meg Tong*, Tomek Korbak, Daniel Kokotajlo, Owain Evans (2023)
Introduces the concept of "out of context learning", and methods for measuring situational awareness in large language models.
See all my publications on Google Scholar →

Contact

🦅 Email 🦉 Google Scholar 🐦 Twitter 🦆 LinkedIn 🐧 GitHub 🦜 Substack