flâneur — a map of the web's best reading

Agency engineering: is AI-alignment "to human intent" enough? - LessWrong

lesswrong.com · 3,663 words · saved by 1 readers

TL;DR: We have not solved the "free will" problem: i.e. we do not know to what extent consciousness, culture, biology or a myriad of other factors shape human will and intent. Yet, prediction of futu…

x Agency engineering: is AI-alignment "to human intent" enough? — LessWrong Agency AI Risk Forecasting & Prediction Free Will AI Frontpage 9 Agency engineering: is AI-alignment "to human intent" enough? by catubc 2nd Sep 2022 8 min read 10 9 TL;DR: We have not solved the "free will" problem: i.e. we do not know to what extent consciousness, culture, biology or a myriad of other factors shape human will and intent. Yet, prediction of future behavior of self and other agent-caused actions (i.e. what the self/others intend) is the main driving force in the evolution of brains; AI technologies wil

Explore this link on the map →

related reading