The Funniest Version of Orthogonality: Human Values Turn Out to Be the Stupid Ones
jessi_cata · x · 2026-10-10
A philosophical riff on the orthogonality thesis: the author argues the funniest way it could hold is if especially stupid values exist (as even Bostrom concedes — ones incompatible with sufficiently high intelligence), no especially smart values exist, and human values themselves count as especially stupid. They add that the easiest way to give an AI a stupid goal is to specifically contradict an Omohundro drive, perhaps combined with high time preference.
Related event: An Ironic Twist on the Orthogonality Thesis(2 posts)→
More from AGI Musings
- Terence Tao on AI proofs: clever ideas, but no humans left to explain them — burny_tech · 2026-10-10
- PhD advisor's context-switching skill maps directly to managing AI agents — Michael_J_Black · 2026-10-10
- Philosophers clash over a taxonomy of consciousness theories, from dualism to IIT — burny_tech · 2026-10-10
- Consciousness theories roasted in one thread: functionalism, IIT dismissals and solipsism — burny_tech · 2026-10-10
- Ex-Cohere researcher mocks 'strategic accounting innovation' at Bay Area AI labs — suchenzang · 2026-10-10
- People Fear AI Taking Their Jobs, Not Losing the Commute and Meetings — rand_longevity · 2026-10-10