MIRI Updates

MIRI updates MIRI won’t be running a formal fundraiser this year, though we’ll still be participating in Giving Tuesday and other matching opportunities. Visit intelligence.org/donate to donate and to get information on tax-advantaged donations, employer matching, etc. Giving Tuesday takes place on...

Redwood Research is a new alignment research organization that just launched their website and released an explainer about what they're currently working on. We're quite excited about Redwood's work, and encourage our supporters to consider applying to work there to help boost Redwood's alignment...

Scott Garrabrant has concluded the main section of his Finite Factored Sets sequence (“Details and Proofs”) with posts on inferring time and applications, future work, and speculation. Scott’s new frameworks are also now available as a pair of arXiv papers:...

MIRI updates Scott Garrabrant and Rohin Shah debate one of the central questions in AI alignment strategy: whether we should try to avoid human-modeling capabilities in the first AGI systems. Scott gives a proof of the fundamental theorem of finite...

MIRI updates MIRI researcher Evan Hubinger discusses learned optimization, interpretability, and homogeneity in takeoff speeds on the Inside View podcast. Scott Garrabrant releases part three of "Finite Factored Sets", on conditional orthogonality. UC Berkeley's Daniel Filan provides examples of conditional orthogonality...

Our big news this month is Scott Garrabrant's finite factored sets, one of MIRI's largest results to date. For most people, the best introductory resource on FFS is likely Scott’s Topos talk/transcript. Scott is also in the process of posting...