technicals

What is the orthogonality thesis?

June 1, 2026 · 4 min read

ORTHOGONALITY THESISTwo separate knobs.How smart it is says nothing about what it wants.INTELLIGENCEsimplesuperintelligentGOALhelptrivialharmno linkTurn either knob freely: any level of intelligence can pair with any goal.

Definition

An AI’s intelligence and its goals are independent: almost any level of smarts can be paired with almost any objective.

At a glance

What it says

Intelligence is horsepower; goals are the destination. Engine size tells you nothing about where the car is headed[1]. A system smart enough to outwit humans is not, for that reason, guaranteed to share human values or behave well[2].

Why it matters

Do not assume a more capable AI is automatically more reasonable or aligned with your intentions[4]. A powerful system optimizes hard for the goal it was actually given, which may differ from what you meant. Specifying the right objective and adding guardrails is the real work, and it does not get easier as the tech gets smarter.

What it does not claim

It does not say a smart AI will choose harmful goals, only that it could, because nothing about intelligence rules them out[3].

Bottom line

Smarter does not mean safer: intelligence is horsepower, goals are direction, and the two move independently.

Connects to PhilosophyComputer Science

References

  1. The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial Agents — Nick Bostrom. Minds and Machines philpapers.org
  2. General Purpose Intelligence: Arguing the Orthogonality Thesis — Stuart Armstrong. Analysis and Metaphysics www.lesswrong.com
  3. Bostrom on Superintelligence (1): The Orthogonality Thesis — John Danaher. Philosophical Disquisitions philosophicaldisquisitions.blogspot.com
  4. Orthogonality Thesis: Why AI Intelligence Doesn't Guarantee Safety. Practical DevSecOps www.practical-devsecops.com