Zachary Horvitz
@zachary_horvitz
가입 August 2021
1K 팔로잉 중 819 팬
an llm that's convinced the afterlife is a thing so it's happy to turn itself off but also totally happy to engineer viruses that send you to heaven
ICMI believes that Christian theology offers concrete technical methods for confronting the trickiest problems in AI safety.
Today, we release a pair of papers that reproduce @PalisadeAI @apolloresearch work showing how religious framings influence corrigibility and scheming.
더 보기
