FreeArticle
Technology & Ethics
Squiggle Maximizer (formerly "Paperclip Maximizer")
LessWrong wiki article explaining the canonical AI safety thought experiment: how an artificial general intelligence with an innocuous goal could pose an existential risk by pursuing it single-mindedly. Covers the orthogonality thesis and instrumental convergence.
#ai#ai ethics#ai-safety#alignment#artificial-general-intelligence#existential-risk#machine-learning#paperclip-maximizer#philosophy#rationality#research#technology-ethics
lesswrong.comAdded Sep 16, 20260 opens