I'm a researcher at the Machine Intelligence Research Institute. I've lived in the Bay Area since 2013, when I moved here from Australia. I try to work to make the future good for sentient beings; at the moment I believe that working on existential risk from artificial intelligence is my best bet for doing this.
Within computer science I like functional programming and data structures; other areas of science I like include the physics that leads to chemistry (that is, the nonrelativistic quantum mechanics of electrons), evolutionary theory, and cell biology.
Some fun projects I've worked on include the following:
Blog (All posts) (Best posts) (RSS)
- An analogy between thermodynamics and economics
- Why is food so energy dense?
- Why can't an air conditioner expel heat through the power cord?
- Is fining the victims of crimes just as good as fining criminals at preventing crimes?
- Some thoughts on EA outreach to high schoolers
- Thoughts on criticism
- How good is humanity at coordination?
- Six economics misconceptions of mine which I've resolved over the last few years
- Some thoughts on deference and inside view models
- My personal cruxes for working on AI safety
- Thoughts on doing good through non-standard EA career pathways
- Three underrated science facts
- Bayes Theorem being surprisingly aggressive
- My EA forum AMA
- In what way are CNNs really biologically inspired?
- You can quickly get a sense of a field by hiring tutors who are experts in it
- Reverse physics
- Why aren't the Sun and Jupiter blurry?
- 'Other people are wrong' vs 'I am right'
- Why I'm less of a hedonic utilitarian than I used to be
- A surprisingly hard CS problem: sums of square roots
- The weirdest ideas I take seriously
- Kelly betting and Bayesian inference
- Looking at the Schrödinger equation radially
- Uncontroversial opinion: the internment of Japanese Americans was bad