PatrickL

Earlier this year, Vaniver recommended Bug Bounties for Advanced ML Systems. I spent a while at Rethink Priorities considering and expanding on this idea, suggesting potential program models, and assessing the benefits and risks of programs like this, which I've called 'AI Safety Bounties': Short summary AI safety bounties are...

Summary This document looks at the predictions made by AI experts in The 2016 Expert Survey on Progress in AI, analyses the predictions on ‘Narrow tasks’, and gives a Brier score to the median of the experts’ predictions. My analysis suggests that the experts did a fairly good job of...