The AI Alignment Forum has left beta! Dovetailing with the launch, MIRI researchers Scott Garrabrant and Abram Demski will be releasing a new sequence introducing our research over the coming week, beginning here: Embedded Agents. (Shorter illustrated version here.) Other...
Summer MIRI Updates: Buck Shlegeris and Ben Weinstein-Raun have joined the MIRI team! Additionally, we ran a successful internship program over the summer, and we’re co-running a new engineer-oriented workshop series with CFAR. On the fundraising side, we received a...
Updates New posts to the new AI Alignment Forum: Buridan’s Ass in Coordination Games; Probability is Real, and Value is Complex; Safely and Usefully Spectating on AIs Optimizing Over Toy Worlds MIRI Research Associate Vanessa Kosoy wins a $7500 AI...
Updates A new paper: “Forecasting Using Incomplete Models“ New research write-ups and discussions: Prisoners’ Dilemma with Costs to Modeling; Counterfactual Mugging Poker Game; Optimization Amplifies Eliezer Yudkowsky, Paul Christiano, Jessica Taylor, and Wei Dai discuss Alex Zhu’s FAQ for Paul’s...
Updates New research write-ups and discussions: Logical Inductors Converge to Correlated Equilibria (Kinda) MIRI researcher Tsvi Benson-Tilsen and Alex Zhu ran an AI safety retreat for MIT students and alumni. Andrew Critch discusses what kind of advice to give to...
Updates New research write-ups and discussions: Resource-Limited Reflective Oracles; Computing An Exact Quantilal Policy New at AI Impacts: Promising Research Projects MIRI research fellow Scott Garrabrant and associates Stuart Armstrong and Vanessa Kosoy are among the winners in the second...
