A misalignment taxonomy

·LessWrong··

I am going to discuss five kinds of inner misalignment and two kinds of outer misalignment, which create a simple taxonomy of alignment failure modes. When I talk about a kind of misalignment here, I am talking about a reason for misalignment (like inner/outer misalignment), not a kind of misaligned agent (like a schemer versus a fitness-seeker), although they can be related. It is possible that multiple of these failure modes could occur in unison; I am attempting to describe independent, but p...

Read full article →

Related Articles

Xbox goes down. You can't play games you own on disc
surprisetalk · Hacker News · 1d ago
Civilian plane crash in New Mexico tied to military GPS blocking
dzdt · Hacker News · 2h ago
Ten advances in mathematics and theoretical computer science
milkshakes · Hacker News · 1d ago
Oxide Computer raises $445M (SEC Form D)
depr · Hacker News · 17h ago
Mistral's Shieldstral: 3B open-weights model for multimodal moderation
riadsila · Hacker News · 21h ago