RSS

bfitzgerald3132

Karma: 4

AI mod­els in­her­ently al­ter “hu­man val­ues.” So, al­ign­ment-based AI safety ap­proaches must bet­ter ac­count for value drift

bfitzgerald3132Jan 13, 2025, 7:22 PM
5 points
2 comments13 min readLW link