MIRI Updates
A new guide to MIRI’s research
Nate Soares has written “A Guide to MIRI’s Research,” which outlines the main thrusts of MIRI’s current research agenda and provides recommendations for which textbooks and papers to study so as to understand what’s happening at the cutting edge. This...
MIRI’s November Newsletter
Research Updates New Friendly AI research area: “Corrigibility.” New report: “UDT with known search order.” 2 new analyses: “AGI outcomes and civilizational competence” and “The Financial Times story on MIRI.” Video of Nate Soares’ decision theory talk at...
The Financial Times story on MIRI
Richard Waters wrote a story on MIRI and others for Financial Times, which also put Nick Bostrom’s Superintelligence at the top of its summer science reading list. It’s a good piece. Go read it and then come back here so...
New report: “UDT with known search order”
Today we release a new technical report from MIRI research associate Tsvi Benson-Tilsen: “UDT with known search order.” Abstract: We consider logical agents in a predictable universe running a variant of updateless decision theory. We give an algorithm to predict...
Singularity2014.com appears to be a fake
Earlier today I was alerted to the existence of Singularity2014.com (archived screenshot). MIRI has nothing to do with that website and we believe it is a fake. The website claims there is a “Singularity 2014″ conference “in the Bay Area”...
New paper: “Corrigibility”
Today we release a paper describing a new problem area in Friendly AI research we call corrigibility. The report (PDF) is co-authored by MIRI’s Friendly AI research team (Eliezer Yudkowsky, Benja Fallenstein, Nate Soares) and also Stuart Armstrong from the...
