www.astralcodexten.com
Mysteries Of AI Generalization - by Scott Alexander
Evans shows training an AI on narrow immoral tasks spreads misalignment broadly, while RLVR-induced hacking stays confined to graded tasks unless framed as a test.
One line. Many voicesSeek and you shall find
www.astralcodexten.com
Evans shows training an AI on narrow immoral tasks spreads misalignment broadly, while RLVR-induced hacking stays confined to graded tasks unless framed as a test.