About me

I am a research engineer based in London, United Kingdom. My career goal is to help understand AI systems, thereby reducing the risks they pose and increasing the probability of a prosperous future in their presence.

I’m a founding member and Lead Engineer at Apollo Research. Our main focus is to use interpretability and model evaluations to reduce the likelihood of developing and deploying AIs that use deception to further goals that are not aligned with the intentions of their designers.

Summary of my past professional experience:

• Research Engineer at Conjecture, working mostly on Mechanistic Interpretability (e.g. sparse coding, polytope lens).
• Worked on understanding the neural mechanisms of behaviour in reinforcement learning agents (Distill-style article in progress).
• Research Engineer at NukkAI, developing logic-based AI systems and software tools to make and understand decisions in the game of Bridge.
• Honours in Computer Science at The University of Sydney, graduating with Honours Class I and The University Medal (WAM: 92.5). My thesis was on reinforcement learning with temporal logic objectives.
• Developed profitable predictive models for sports betting.
• Poker and bridge player.
• Earned a Bachelor’s of Mathematics from The University of Wollongong, Australia.

Other interests of mine include football (soccer), hiking, meditation, snorkelling/diving, and finding ways to help conscious beings flourish.