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

Scott Alexander humorously analyzes 'My Immortal' as an alchemical allegory, combining medieval alchemy, Rosicrucian writings, and Goethe's Faust. Longer summary

Scott Alexander presents a satirical analysis of the infamous Harry Potter fanfiction 'My Immortal', arguing that it is actually a complex alchemical allegory combining medieval alchemy, Rosicrucian writings, and Goethe's Faust. He breaks down the story's structure, characters, and symbolism, drawing parallels to alchemical stages and concepts. The post is written in a tongue-in-cheek manner, mimicking academic literary analysis while applied to a notoriously bad piece of writing. Shorter summary