We’re excited to release a new AI governance research agenda from the MIRI Technical Governance Team. With this research agenda, we have two main aims: to describe the strategic landscape of AI development and to catalog important governance research questions....
[mathjax] This is the edited transcript of a talk introducing finite factored sets. For most readers, it will probably be the best starting point for learning about factored sets. Video: (Lightly edited) slides: https://intelligence.org/files/Factored-Set-Slides.pdf (Part 1, Title Slides)...
Evan Hubinger, Chris van Merwijk, Vladimir Mikulik, Joar Skalse, and Scott Garrabrant have a new paper out: “Risks from learned optimization in advanced machine learning systems.” The paper’s abstract: We analyze the type of learned optimization that occurs when a...
MIRI Research Associate Vanessa Kosoy has written a new paper, “Delegative reinforcement learning: Learning to avoid traps with a little help.” Kosoy will be presenting the paper at the ICLR 2019 SafeML workshop in two weeks. The abstract reads: Most...
MIRI Research Associate Vanessa Kosoy has a paper out on issues in naturalized induction: “Forecasting using incomplete models”. Abstract: We consider the task of forecasting an infinite sequence of future observations based on some number of past observations, where the...
Goodhart’s Law states that “any observed statistical regularity will tend to collapse once pressure is placed upon it for control purposes.” However, this is not a single phenomenon. In Goodhart Taxonomy, I proposed that there are (at least) four different...