Frontier lab researcher: "we do not know how to reliably instil values into AIs"

austinc3301 · x · 2026-11-16

Garrison Lovely calls it "one of the most disturbing facts in the world," quoting frontier lab researcher Neel Nanda: "I work at a frontier lab, we do not know how to reliably instil values into the AIs, this is the scientific consensus."

Related event: DeepMind Researcher Admits Labs Still Can't Reliably Instill Values in AI(4 posts)→

Original post →

More from AGI Musings

AGI Musings channel →