Scott Alexander examines Redwood Research's attempt to create an AI that avoids generating violent content, using Alex Rider fanfiction as training data. Longer summary

Scott Alexander reviews Redwood Research's project to create an AI that can classify and avoid violent content in text completions, using Alex Rider fanfiction as training data. The project aimed to test whether AI alignment through reinforcement learning could work, but ultimately failed to create an unbeatable violence classifier. The article explores the challenges faced, the methods used, and the implications for broader AI alignment efforts. Shorter summary

A compilation of 30 diverse links on various topics including science, history, technology, and culture, with brief commentaries by Scott Alexander. Longer summary

This post is a collection of 30 diverse links and brief discussions on various topics. It covers a wide range of subjects including scientific findings, historical anecdotes, technological developments, cultural phenomena, and current events. The post touches on topics such as oil spills, architecture, IQ research, chronic pain therapy, alcohol consumption, AI safety, and more. Scott Alexander provides short commentaries or explanations for each link, often adding his own insights or connecting the information to broader themes. Shorter summary