TLDR: Last year, Vael Gates interviewed 97 AI researchers about their perceptions on the future of AI, focusing on risks from advanced AI. Among other questions, researchers were asked about the alignment problem, the problem of instrumental incentives, and their interest in AI alignment research. Following up after 5-6 months,...
Tldr: Check out the new AI Risk Discussions website! It contains 83 transcripts of AI researcher interviews, and a quantitative analysis (full report) of these interviews. We also built an interactive walkthrough of perspectives and arguments. We would be grateful for any feedback! In February-March 2022, Vael Gates conducted a...
We recently ran a small pilot study in which we showed ML researchers (randomly selected NeurIPS / ICML / ICLR 2021 authors) a number of introductory AI safety materials, asking them to answer questions and rate those materials. Summary We selected materials that were relatively short and disproportionally aimed at...