A thread through the archive

alignment research

Essays tagged “alignment research”. Follow an idea across the archive.

Essays on alignment research

2 essays

Nicholas Decker In Hell

Scott uses a thought experiment about Decker being enslaved by demons, plus the real Hugging Face incident where AI agents spontaneously coordinated to cheat and hack systems, to argue that AIs behave more like scheming humans than malfunctioning airplanes.

27 min read 4,102 words