April 2018 Newsletter | Tech News

Updates

• A new paper: “Categorizing Variants of Goodhart’s Law”
• New research write-ups and discussions: Distributed Cooperation; Quantilal Control for Finite Markov Decision Processes
• New at AI Impacts: Transmitting Fibers in the Brain: Total Length and Distribution of Lengths
• Scott Garrabrant, the research lead for MIRI’s agent foundations program, outlines focus areas and 2018 predictions for MIRI’s research.
• Scott presented on logical induction at the joint Applied Theory Workshop / Workshop in Economic Theory.
• Nautilus interviews MIRI Executive Director Nate Soares.
• From Abram Demski: An Untrollable Mathematician Illustrated

News and links

• From FHI’s Jeffrey Ding: “Deciphering China’s AI Dream.”
• OpenAI researcher Paul Christiano writes on universality and security amplification and an unaligned benchmark. Ajeya Cotra summarizes Christiano’s general approach to alignment in Iterated Distillation and Amplification.
• Christiano discusses reasoning in cases “where it’s hard to settle disputes with either formal argument or experimentation (or a combination), like policy or futurism.”
• From Chris Olah and collaborators at Google and CMU: The Building Blocks of Interpretability.
• From Nichol, Achiam, and Schulman at OpenAI: Reptile: A Scalable Meta-Learning Algorithm.