Why I joined AISI by Geoffrey Irving | AISI Work
aisi.gov.uk · 939 words · saved by 1 readers
Our Chief Scientist, Geoffrey Irving, on why he joined the UK AI Safety Institute and why he thinks other technical folk should too
Note to readers: we changed our name to the AI Security Institute on 14 February 2025. Read more here. Coordination is important and under-resourced (This is a long-form version of an earlier tweet thread .) I’ve been working on AI and machine learning for 10 years, including leading the Reflection Team at OpenAI and the Scalable Alignment Team at DeepMind. But this year, for the first time, I took a job in the government and joined the UK AI Safety Institute. People often ask me why I did this (often because they are considering a similar leap). I continue to think direct technical work on AI
related reading
- Reflections on AISI | naml.usnaml.us
- I'm Switching Into AI Safetyalexirpan.com
- Making sense of the UK’s AI Security Instituteadalovelaceinstitute.org
- Leaving Open Philanthropy, going to Anthropic - Joe Carlsmithjoecarlsmith.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Ten AI safety projects I'd like people to work onthirdthing.ai
- The case for AI safety capacity-building worksubstack.com
- The case for AI safety capacity-building workmultipliercg.substack.com
- AI Safety is Bottlenecked - Opportunity for Impact is Highbriandavies.substack.com
- We have 3 years to solve alignment before superintelligenceyoutube.com
- AGI safety career advice — EA Forumforum.effectivealtruism.org
- Ten AI safety projects I'd like people to work on — LessWronglesswrong.com