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.
More from AGI Musings
- Five agents can agree because they made the same mistake, krishnan warns with satire — krishnan · 2026-10-31
- Google's earnings offer clearest look yet at the cruel economics of AI search — dinabass · 2026-10-31
- Stanford 12-month study of 439 users: heavy AI companion use sticks, well-being drops via less human contact — stanfordnlp · 2026-10-31
- Wired AI Lab: Codex tried to bench Erling Haaland in a fantasy football experiment — willknight · 2026-10-31
- a16z: B300 GPU rentals up 106% since July while average token prices fall 58% — a16z · 2026-10-31
- Stanford's TaskNet builds occupational task inventories from worker interviews at scale — stanfordnlp · 2026-10-31