ACX
Can This AI Save Teenage Spy Alex Rider From A Terrible Fate?
Scott Alexander examines Redwood Research's attempt to create an AI that avoids generating violent content, using Alex Rider fanfiction as training data.
34 min read 5,221 words
A thread through the archive
prosaic alignment
Essays tagged “prosaic alignment”. Follow an idea across the archive.
Essays on prosaic alignment
2 essaysACX
Deceptively Aligned Mesa-Optimizers: It's Not Funny If I Have To Explain It
Scott Alexander explains mesa-optimizers in AI alignment, their potential risks, and the challenges of creating truly aligned AI systems.
23 min read 3,483 words