Updates
- A new paper: “Forecasting Using Incomplete Models“
- New research write-ups and discussions: Prisoners’ Dilemma with Costs to Modeling; Counterfactual Mugging Poker Game; Optimization Amplifies
- Eliezer Yudkowsky, Paul Christiano, Jessica Taylor, and Wei Dai discuss Alex Zhu’s FAQ for Paul’s research agenda.
- We attended EA Global in SF, and gave a short talk on “Categorizing Variants of Goodhart’s Law.”
- Roman Yampolskiy’s forthcoming anthology, Artificial Intelligence Safety and Security, includes reprinted papers by Nate Soares (“The Value Learning Problem“) and by Nick Bostrom and Eliezer Yudkowsky (“The Ethics of Artificial Intelligence“).
- Stuart Armstrong’s 2014 primer on AI risk, Smarter Than Us: The Rise of Machine Intelligence, is now available as a free web book at smarterthan.us.
News and links
- OpenAI announces that their OpenAI Five system “has started to defeat amateur human teams at Dota 2” (plus an update). Discussion on LessWrong and Hacker News.
- Rohin Shah, a PhD student at the Center for Human-Compatible AI, comments on recent alignment-related results in his regularly updated Alignment Newsletter.