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...
Research Updates Our major project last month was our Friendly AI technical agenda overview and supporting papers, the former of which is now in late draft form but not yet ready for release. 4 new expert interviews, including...
Thanks to the generosity of 100+ donors, we successfully completed our 2014 summer matching challenge on August 15th, raising more than $400,000 total for our research program. Our deepest thanks to all our supporters! Research updates New...
Dear friends, Our summer matching challenge is underway! Every donation made to MIRI between now and August 15th, 2014 will be matched dollar-for-dollar, up to a total of $200,000! Please donate now to help support our research! Research Updates May...
Research Updates Two new reports: “Distributions allowing tiling of staged subjective EU maximizers” and “Non-omniscience, probabilistic inference, and metamathematics.” New analysis: Failures of an embodied intelligence. Book chapter co-authored by Nick Bostrom (Oxford) and Eliezer Yudkowsky (MIRI) now published in...
Dear friends, The SV Gives fundraiser was a big success for many organizations, and especially for MIRI. Thanks so much, everyone! Research Updates Two new papers: “Program equilibrium…” (accepted to the MIPC workshop at AAAI-14) and “Problems of self-reference…” (accepted...
