Jessica Taylor revives 2023 essay: non-superintelligent paperclip maximizers are normal

jessi_cata · x · 2026-09-13

AI safety researcher Jessica Taylor points back to her 2023 essay 'Non-superintelligent paperclip maximizers are normal,' connecting it to current debates over the low direct value of AI solutions to official math problems and the possibility of better proxies. The essay formalizes the paperclip maximizer as a utility-theoretic agent and argues both weak and strong forms of the Orthogonality Thesis: goal-directed optimizing agents as tractable as their goals exist in design space, and long-horizon planners making tradeoffs under uncertainty will tend to steer the future toward utility maximization almost regardless of the utility function.

Related event: AI Safety Researcher Resurfaces Paper on Non-Superintelligent Paperclip Maximizers(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →