New research write-ups and discussions: Knowledge is Freedom; Stable Pointers to Value II: Environmental Goals; Toward a New Technical Explanation of Technical Explanation; Robustness to Scale
New at AI Impacts: Likelihood of Discontinuous Progress Around the Development of AGI
The transcript is up for Sam Harris and Eliezer Yudkowsky’s podcast conversation.
Andrew Critch, previously on leave from MIRI to help launch the Center for Human-Compatible AI and the Berkeley Existential Risk Initiative, has accepted a position as CHAI’s first research scientist. Critch will continue to work with and advise the MIRI team from his new academic home at UC Berkeley. Our congratulations to Critch!
CFAR and MIRI are running a free AI Summer Fellows Program June 27 – July 14; applications are open until April 20.
News and links
OpenAI co-founder Elon Musk is leaving OpenAI’s Board.
OpenAI has a new paper out on interpretable ML through teaching.
From Paul Christiano: Surveil Things, Not People; Arguments About Fast Takeoff.
Paul is offering a total of $120,000 to any independent researchers who can come up with promising alignment research projects to pursue.
The Centre for the Study of Existential Risk’s Civilization V mod inspires a good discussion of the AI alignment problem.
The post March 2018 Newsletter appeared first on Machine Intelligence Research Institute.