Robustly Beneficial group

The Robustly Beneficial group is an AI ethics group, started by Louis Faucon and Sergei Volodin, in Lausanne, Switzerland. The group is now managed by Louis Faucon, El Mahdi El Mhamdi and Lê Nguyên Hoang. Every week, we discuss a paper relevant to AI ethics. Please feel free to ask to join.

Past papers

• WeBuildAI: Participatory Framework for Algorithmic Governance, PACMHCI. LKKKY+19.
• A Roadmap for Robust End-to-End Alignment. Hoang18 RB8.
• Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model. SAHSS+19 RB7.
• Intelligent Autonomous Things on the Battlefield. AI for the Internet of Everything. KottStump19 RB6.
• Efficient Learning from Comparisons. MaystrePhD18 RB5.
• Focusing on the Long-Term: It's Good for Users and Business. KDD. HOT15 RB4.
• Experimental evidence of massive-scale emotional contagion through social networks. PNAS. KGH14 RB3.
• Recent Advances in Algorithmic High-Dimensional Robust Statistics. DiakonikolasKane19 RB2.
• Algorithmic Accountability Reporting: On the Investigation of Black Boxes. Diakopoulos14 RB1.
• Efficient and Thrifty Voting by Any Means Necessary, NeurIPS. MPSW19.
• The Vulnerable World Hypothesis, Global Policy. Bostrom19.
• Occam's razor is insufficient to infer the preferences of irrational agents, NeurIPS. ArmstrongMindermann18.
• Supervising strong learners by amplifying weak experts. CSA18.
• Embedded Agency. DemskiGarrabrant19.
• Concrete Problems in AI Safety. AOSCSM16.
• The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial Agents, Minds and Machines. Bostrom12.
• On the Limits of Recursively Self-Improving AGI, AGI. Yampolski15.
• Can Intelligence Explode? Hutter12.
• Risks from Learned Optimization in Advanced Machine Learning Systems. HMMSG19.
• The Value Learning Problem, IJCAI. Soares16.

Candidate future papers

• Why Philosophers Should Care About Computational Complexity, ECCC. Aaronson11.
• Facebook language predicts depression in medical records, PNAS. ESMUC+18.
• Exposure to opposing views on social media can increase political polarization, PNAS. BABBC+18.
• Multi-armed Bandit Models for the Optimal Design of Clinical Trials: Benefits and Challenges, Statistical science: a review journal of the Institute of Mathematical Statistics. VBW15.
• The complexity of agreement, STOC. Aaronson05.
• Reward Tampering Problems and Solutions in Reinforcement Learning. EverittHutter19.
• AGI safety literature review, IJCAI. ELH18.
• The global landscape of AI ethics guidelines, Nature. JIV19.
• Tackling climate change with machine learning. RDKKL+19.
• Science and Environmental Communication via Online Video: Strategically Distorted Communications on Climate Change and Climate Engineering on YouTube, Frontiers. Allgaier19
• An fMRI Investigation of Emotional Engagement in Moral Judgment GSNDC01
• Reflections on Trusting Trust. Turing Award Lecture. Thompson84