✳flâneur — a map of the web's best reading

Risks from AI persuasion - AI Alignment Forum

alignmentforum.org · 11,105 words · saved by 1 readers

A case for why persuasive AI might pose risks somewhat distinct from the normal power-seeking alignment failure scenarios. …

x Risks from AI persuasion — AI Alignment Forum AI Persuasion AI Frontpage 31 Risks from AI persuasion by Beth Barnes 24th Dec 2021 38 min read 15 31 A case for why persuasive AI might pose risks somewhat distinct from the normal power-seeking alignment failure scenarios. Where I'm currently at: I feel moderately confident that powerful persuasion is useful to think about for understanding AI x-risk, but unsure whether it's best regarded as its own threat, as a particular example of alignment difficulty, or just as a factor in how the world might change over the next decade or two. I think thi

Explore this link on the map →

related reading