(Posting as a comment since I’m not really answering your actual question.)
I think if you find something within AI safety that is intellectually motivating for you, this will more likely than not be your highest-impact option. But FWIW here are some pieces that are mathy in one way or another that in my view still represent valuable work by impact criteria (in no particular order):
Absolutely agree with everything you’ve said here! AI safety is by no means the only math-y impactful work.
Most of these don’t quite feel like what I’m looking for, in that the math is being used to do something useful or valuable but the math itself isn’t very pretty. “Racing to the Precipice” looks closest to being the kind of thing I enjoy.
(Posting as a comment since I’m not really answering your actual question.)
I think if you find something within AI safety that is intellectually motivating for you, this will more likely than not be your highest-impact option. But FWIW here are some pieces that are mathy in one way or another that in my view still represent valuable work by impact criteria (in no particular order):
Could Advanced AI Drive Explosive Economic Growth?
Report on Semi-informative Priors [relevant to AI timelines]
Racing to the precipice: a model of artificial intelligence development
Why we can’t take expected value estimates literally (even when they’re unbiased)
The epistemic challenge to longtermism
Philanthropy Timing and the Hinge of History (and other work on this by Phil Trammell)
Dissolving the Fermi Paradox
The Simulation Hypothesis Undercuts the SIA/Great Filter Doomsday Argument
Statistical Normalization Methods in Interpersonal and Intertheoretic Comparisons
Replicating and extending the grabby aliens model
Cost-effectiveness of research
The timing of labour aimed at reducing existential risk
Effectiveness is a Conjunction of Multipliers
Absolutely agree with everything you’ve said here! AI safety is by no means the only math-y impactful work.
Most of these don’t quite feel like what I’m looking for, in that the math is being used to do something useful or valuable but the math itself isn’t very pretty. “Racing to the Precipice” looks closest to being the kind of thing I enjoy.
Thank you for the suggestions!