(some thinkers who have influenced me)
The journey of a form along the line of time
a form impregnating the barren line of time
a form conscious of an image
that returns from a feast in a mirror.
— Forough Farrokhzad
Share anonymous feedbackI am a Principal Investigator at the University of Oxford, where I lead the Technical Safety & Governance (TSG) Lab. I am also a Governing Body Fellow in AI & ML at Reuben College and Technical Director of the AI Governance Initiative.
My research looks inside neural networks to understand how they work, and asks whether that understanding can help us evaluate, control, and govern AI systems.
Other appointments: Visiting Assistant Professor at Tsinghua University; Honorary Fellow at the University of Edinburgh; Member of Technical Staff at Martian.
I am looking for students, and committed to supporting researchers from disadvantaged or underrepresented backgrounds.
New News
| Oct 2026 | Appointed Honorary Fellow at the School of Informatics, University of Edinburgh. |
|---|---|
| Oct 2026 | Three papers accepted at NeurIPS 2026. Appeared on Al Jazeera English to discuss AI risks, control, and governance. |
| Sep 2026 | Joined Reuben College as a Governing Body Fellow in AI & Machine Learning. Published an Oxford Expert Comment, “Flying blind into the AI age,” with Maike Osborne, on evaluating and governing increasingly autonomous AI systems. Interviewed by Deutsche Welle and CNN-News18 on AI control, frontier AI risks, and governance. |
| Sep 2026 | Quoted in France24 on AI control and existential risk; an invited talk at the eXCV Workshop, ECCV 2026; and serving as Area Chair for ICLR 2027. |
| Aug 2026 | Live television interview on Sky News’ Morning Show, discussing safety around humanoid robots. One paper accepted at EMNLP 2026 and one at COLM 2026. |
| Jul 2026 | Invited speaker at EIML@ICML 2026 (2nd Workshop on Epistemic Intelligence in Machine Learning). Talk: “Understanding model behaviour in the age of AGI.” |
| Jul 2026 | Teaching at two summer schools: invited lecture at the ML Summer School on Reliability and Safety, Kraków (Jul 1–4); and at the Oxford Machine Learning Summer School (OxML 2026), Track 02: Representation Learning & Generative AI (Jul 15–18). |
| Jun 2026 | Several upcoming invited talks: debating AI governance at the Oxford Union (Connected Life Summit, Jun 25); invited talk at ETH Zürich on automated interpretability (Jun 25, remote); speaking at BLISS (Berlin Learning and Intelligent Systems Society) Speaker Series, Berlin (Jun 30); and a talk at the Foresight Secure & Sovereign AI Workshop, Berlin (Jul 18–19). |