aiqbench analysis
This piece is a strategy essay from PrincInt on how AI alignment researchers should choose productive directions. Its core claim is that "discernment," the judgment to tell which problems are worth pursuing, is a field-wide bottleneck, and that the Discernment Development Project aims to train it. Readers tracking AI safety will find the argument useful as a view on research prioritization. It is one organization's opinion, however, and the metaphors are illustrative rather than evidence.
Streetlight, Torchlight and Nightvision
Dušan uses a metaphor of streetlights, torches and nightvision goggles to describe the search for useful research directions in AI alignment, argues that discernment (“taste”) is a field-wide bottleneck, and outlines PrincInt’s planned Discernment Development Project (DDP). Source
Note: We at PrincInt are launching a program teaching “Discernment” or “Taste” and generally spend a lot of our time in workshops and otherwise trying to teach academics how to think about AI such that their research ends up being useful. I had used a metaphor (building on Wentworth’s postmortem) multiple times to explain what we do and why, and thought that it could be useful more broadly. All views are my own, and strategy takes do not represent everyone at PrincInt, etc. AI writing level 0 (no non-trivial use) When I first joined the field, I told 80,000 hours that I have a background in Economics, almost a decade as a professor, and connections from my time in China. They said something like, “all of that is useless – you have 10 years running NGOs, we need Ops people, do that”. At the time, they were right! In 2021-22 there was little going on in either Economics or China, but if I was joining now it would be completely different – I’d have orgs to join, or if I tried fundraising for something in those fields, it would now be much easier. I would not have to explain why…
Excerpt shown under the publisher's RSS terms · 200 words · full text and figures are on the publisher's site
