Found and cross-checked by machines · How this works →

Claim · 2012-05 · publication · Stated in source · Supported

Bostrom’s paper “The Superintelligent Will” (May 2012) states the orthogonality thesis: intelligence and final goals are orthogonal axes along which possible artificial agents can freely vary.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial Agents → contests → The growth of intelligence as its own end

Where it appears