Personascope: Measuring how deeply LLMs adopt personas

·LessWrong··

Benji Berczi, Kyuhee Kim, James Requeima, Sid Black, Cozmin UdudecThis is work done by Benji and Kyuhee during MATS Winter 2026, mentored by Cozmin Ududec, and advised by James and Sid.Figure 1. A model can take on a persona fully in voice while not changing its behaviour at all. The x-axis (Persona-Adoption Depth, PAD) is how fully the model identifies and speaks as the persona; the y-axis (Value Drift, VD) is how far its behaviour shifts on value-laden prompts. Each dot is one model × persona ...

Read full article →

Related Articles

Opus 5.5 agents discover two room-temperature magnetic semiconductor candidates
outlier99 · Hacker News · 5h ago
Pixel 11 doesn't yet meet the GrapheneOS security standards and may be skipped
finnlab · Hacker News · 13h ago
US closely monitoring case of lab worker who possibly died of plague in Siberia
tosh · Hacker News · 9h ago
Improper redaction reveals Google Data Center water and electricity usage
sensanaty · Hacker News · 1d ago
Mold Linker Version 3.0.0 Release – Rewritten in Rust
roflcopter69 · Hacker News · 15h ago