Getting the public and policy conversation about AI right matters as much as the research itself. I write, speak, and advise on AI safety, interpretability, and governance — for researchers, policymakers, startups, and the public.
Writing & media. I write and comment for a range of outlets, and my work is regularly covered in the press. Selected coverage:
- The Independent / Irish Independent (2026)—AI existential risk and timelines
- The Conversation (2026)—how AI robots can be tricked into unsafe behaviour
- Fortune / Yahoo Tech (2025)—reasoning models more vulnerable to jailbreaks
- VKTR (2025)—how easily AI training data can be poisoned (PoisonBench)
- Raconteur (2025)—quoted on US AI deregulation
Speaking. Keynotes, seminars, and panels at academic and industry venues. → See talks
Advisory. I work with AI startups on safety, interpretability, and security — usually the questions that are hard to get right when you’re small: where to point the research agenda, what benchmarks and datasets to build, how to evaluate your models, and who to hire.
Contact—[firstname][lastname]93[at]gmail[dot]com