Oliver Crook

Computational/modelling problems in biosecurity.

Stream overview

Biosecurity and intersections with AI - either policy related or empirical research that could help policy makers. Synthesis screening etc.

Mentors

Oliver Crook (Olly)
University of Oxford
,
Group Leader
London, Oxford
Policy and Governance
Biosecurity
Capability and Propensity Evaluations
Adversarial Robustness and Safeguards

I am a group leader at the University of Oxford working in protein chemistry and machine learning. Our field has had huge success with AI, but these successes come with potential catastrophic risks. Much of my research focuses on responsible innovation and biosecurity alongside the more academic work in biophysics and protein design. I am interested in empirical studies that can support biosecurity and foundational biosecurity work that sits closer to policy.

Read more

Mentorship style

Typically 1 hour weekly meetings by default. I typically respond on slack quite quickly - some weeks I am not available. You are welcome to chat to my phd students too!

Fellows we are looking for

Computational experience e.g. Python

OR statistical modelling

interest in biosecurity

Project selection

We will construct a project together that best suits the skills and interests of the fellow and what I can reasonably be helpful for.

Streams

The Winter 2026 cohort offers a wide range of research streams led by experts across AI alignment, interpretability, governance, and safety. Each stream provides its own research agenda, methodology, and mentorship focus.

London
Empirical
SF Bay Area
Strategy and Forecasting
SF Bay Area
Systems Security
SF Bay Area
London
Control, Monitoring, Red-Teaming, Scalable Oversight, Scheming & Deception
SF Bay Area
Theory
Agent Foundations
SF Bay Area
Interpretability
SF Bay Area
Interpretability, Monitoring, Dangerous Capability Evals
SF Bay Area
Theory
Interpretability, Model Organisms, Red-Teaming, Safeguards, Scheming & Deception
SF Bay Area
Theory
Interpretability
Grand Rapids
Theory
Agent Foundations
Washington, D.C.
Systems Security
Policy and Governance
Compute Infrastructure, Policy & Governance, Security
London
Theory
Policy and Governance
Dangerous Capability Evals, Compute Infrastructure, Policy & Governance, Strategy & Forecasting
Washington, D.C.
Systems Security
Compute Infrastructure, Security
London
Control, Monitoring
London
Control, Scheming & Deception, Dangerous Capability Evals, Model Organisms, Monitoring
SF Bay Area
Security, Dangerous Capability Evals