I graduated from Oxford University where I studied philosophy, machine learning and theoretical computer science. So far, of all the ideas I’ve encountered about what I ought to do with my life, longtermism makes the most sense to me. Basically, this means my goal is to help make the long-term future as wonderful as possible. Recently, that has involved:
- Trying to clearly state the strongest arguments about why advanced AI might pose an existential threat, as part of an AI Safety Camp.
- Writing a master’s thesis, in which I applied Deep Bayesian Active Learning to the Reward Modelling approach to AI alignment, in order to improve its sample efficiency.
- Spending a summer as a research fellow at the Centre for Effective Altruism.
- Drinking copious amounts of green tea.
- Thinking about how to make my brain work better.
Outside of work, you can find me:
- Exploring authentic relating and NVC.
- Meditating and otherwise getting in touch with my inner six-year-old.
- Practising my favourite forms of idleness, which include cooking, stargazing and going on long walks.
You can read more about my doings on my CV.
A river is said to be insequent if it follows a course that is not controlled by the slope or composition of the rock structure in which it formed. Apparently, some rivers manage to do this, which is kinda neat. Us humans, though, we’re even better than rivers—we were born with that ability. And there lies our ladder to climb to the stars.