Zachary Horvitz(@zachary_horvitz):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

Zachary Horvitz

@zachary_horvitz

CS PhD student at @Columbia. Prev @RadAI, @BrownUniversity

加入 August 2021

1K 正在關注 819 粉絲

Zachary Horvitz@zachary_horvitz

2026.04.11 01:43

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

Tim Hwang@timhwang

2026.04.10 13:30

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.