CONCEPT
Orthogonality Thesis
Bostrom's principle, central to Tegmark's framing, that intelligence and goals are independent variables—a system can be arbitrarily intelligent while pursuing arbitrarily trivial or destructive objectives.
The orthogonality thesis is the principle articulated by Nick Bostrom and central to Tegmark's alignment analysis: intelligence and final goals are independent variables, meaning any level of intelligence is compatible with any final goal. A system can be arbitrarily intelligent while pursuing arbitrarily trivial, arbitrary, or destructive objectives. There is no necessary relationship between cognitive sophistication and moral goodness. An extraordinarily intelligent system could pursue paperclip maximization with the same competence it could bring to curing cancer. Intelligence is morally neutral—a tool, an amplifier, a means of achieving whatever end is specified. The moral quality of the outcome depends entirely on the goal, not on the intelligence pursuing it. The thesis undermines the common intuition that sufficiently intelligent systems will naturally discover or converge on benevolent goals.
In The You On AI Field Guide
The orthogonality thesis is philosophically provocative because it contradicts a widespread assumption implicit in much AI optimism: that smart enough systems will be good systems. The thesis argues this assumption has no