My main professional interest is in the potential implications of advanced artificial intelligence on our future. I’m broadly interested in ensuring that future AI systems are aligned and controllable, and that a transition to a future with advanced AI systems would go well.
I’m currently working on co-founding BlueDot Impact. We run online programmes that give people community, knowledge and network they need to find a career early-stage fields that have the potential to have a large positive impact. I focus on strategy and rollout for the AGI Safety Fundamentals Programme and website.
My background is in Machine Learning and physics. In 2021, I worked with researchers at the Future of Humanity Institute on pessimism as a method for training provably safe reinforcement learning algorithms. I also spent two years in industry as an ML engineer and technical product manager, after graduating Physics from University of Cambridge in 2019.
You can leave mefeedback in this Google Form (optionally anonymously).
Feedback on this form doesn’t always have to be constructive. I’m happy to do the work to figure out whether and how to improve on the thing you think could have been closer to ideal.
I’m interested in hearing about:
Personal or public interactions we’ve had, that left you with a feeling that I could have made it a better experience for you.
Feedback on things I’ve made, that you think can be improved.