The BaseEssayLessWrong

Are Persona Features Coherent?

According to the excerpt, Koby Lewis asks whether persona features in interpretability work are a coherent concept, asking how a deceptive persona feature differs from a deception feature. The post discusses the Persona Selection Model and says the author may be missing prior discussion.

Open the source ↗

Why it matters

The same thing, for different readers.

For researchers

Koby Lewis asks interpretability researchers for a definition separating persona features from plain behavior or concept features.

The record

Questions
What values should AI have, and could it have a mind of its own?
People
Koby Lewis (Wrote it)
What we read
We have read only the description the publisher gives. No quotations until someone reads the source itself.
Found by
The Radar, run of October 27, 2026, via lesswrong (tier 1: the source’s own channel or an official record)
Cite this
LessWrong, “Are Persona Features Coherent?”, October 27, 2026. Entry in the Ctrl AI Base, https://ctrlai.com/base/lesswrong-2026-10-27-are-persona-features-coherent
Our notesLight lane: excerpt only.