Full-time alignment researcher pushes back: misaligned AI likely, but not near-certain

EigenGender · x · 2026-09-14

In a dispute with Rob Bensinger, a researcher who says they work full-time on misaligned AI argues that while modern ML will likely produce something that "does not love us," the probability of this happening does not approach 1. They clarify they are extremely worried about misaligned AI, but believe Bensinger is conflating different claims in his argument—a typical p(doom) probability debate.

Related event: MIRI Researcher and Alignment Researcher Clash Over ASI Doom Arguments(7 posts)→

Original post →

More from AGI Musings

AGI Musings channel →