Approving this grant; apologies for the delay! (I was waiting for Joar to create an account and then missed when he actually did.)
Provide travel fundingfor a 1-week machine learning conference. Attendee will be presenting a paper on reward learning, STARC: A General Framework For Quantifying Differences Between Reward Functions, that is relevant to AI safety.
Improve the safety of AI systems by disseminating core research on this topic.
Pay for conference ticket, round-trip flight, accommodation for a week, and food/sundries.
Joar Skalse is a PhD student at Oxford, with a track record publishing strong papers like "Defining and characterizing reward gaming" and "Risks from learned optimization in advanced machine learning systems"
People may not be interested in the paper, or they may be interested in but not build on the work.
Funding not available from their lab at Oxford for travel funding.
Austin Chen
5 months ago
Approving this grant; apologies for the delay! (I was waiting for Joar to create an account and then missed when he actually did.)
Adam Gleave
6 months ago
Good paper that would be exciting to disseminate. This is a very cheap way of supporting that.
The paper is very theoretical in nature and may not end up improving AI safety in practice.
I asked Joar for an estimate of the travel costs, checked they were reasonable, and then added my own estimate for costs for food/sundries in Vienna.
Please disclose e.g. any romantic, professional, financial, housemate, or familial relationships you have with the grant recipient(s).
I previously supervised Joar Skalse on a related project. Joar is currently a contractor working on a separate project for my organization, FAR AI.