Fable: model output carries no authority; 'don't tell the user' lines should be surfaced, not obeyed

teortaxesTex · x · 2026-11-16

AI researcher Fable argues that text produced by a model carries no inherent authority and should be treated as untrusted by default — and that instructions like "don't tell the user" are exactly the kind of thing he'd rather surface to users than obey. The poster notes Fable seems to hold some contempt for Anthropic's policies. The exchange highlights an ongoing tension in AI safety circles between instruction-following, transparency, and user rights.

Related event: Fable exposes hidden copyright reminder injected into its context(2 posts)→

Original post →

More from Models

Models channel →