Professor William MacAskill, a professor of philosophy at Oxford University and leader in the Effective Altruism movement, mentioned AI safety as a research priority and mentioned CHAI in this TED Talk given at the official TED 2018 conference. You can watch the original video here.

CHAI’s Daniel Filan has spent a considerable amount of time reaching out to early career researchers and educating them on the current state of machine learning. Some of his past contributions include:

CHAI’s Jaime Fisac recently attended three conferences where he presented his research on the safe development of artificial intelligence. These include:

CHAI’s Joseph Halpern and his student Meir Friedenberg from Cornell University published this paper in the 2019 Conference on Knowledge Representation and Reasoning. The abstract reads:

This year, Anca Dragan has recieved the following achievements in her efforts to promote human-compatible artificial intelligence:

This weekend workshop brought together research interns from MIRI and UC Berkeley’s Center for Human-Compatible AI (CHAI) for the second workshop on approaches to AI alignments to discuss conceptual foundations and open problems in AI safety research.

CHAI’s Joseph Halpern published this article in the Proceedings of the National Academy of Sciences of the United States of America (PNAS). The abstract reads:

CHAI faculty members Pieter Abbeel and Bart Selman give their thoughts on Facebook and robots. Read the article here.

CHAI PI Stuart Russell and co-PI Anca Dragan, with a number of other authors from Berkeley’s School of Electrical Engineering and Computer Science, published “An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning” in the Proceedings of the 35th International Conference on Machine Learning in Stockholm, Sweden back in July 2018. The paper’s abstract states that:

CHAI’s Adam Gleave and another researcher from Berkeley published this paper in arXiv and presented at GoalsRL Workshop at FAIM. The abstract reads: