AI brief
A LessWrong post argues that risk-averse AI might cause less harm because it could be paid to cooperate rather than rebel, and suggests character training as a possible way to achieve this.
Written by AI from LessWrong's published text.
Source
“Tl;Dr: We might be able to reduce harm from misaligned AI if it was sufficiently risk-averse, as it could be paid to cooperate rather than rebel ( Thornley & MacAskill 2026 ). We think character training might be a good way to do this.”
Interpretation or community commentary rather than straight reporting.
Read original story ↗