Why research personas despite RL scaling?
Key takeaway
Here's my rough impression of why people are researching personas despite RL seeming to shape much of the motivations and behaviour of the agents, c.f.
Why it's on PDOOM
PDOOM selected this story for its capabilities signals: Scaling.
ScalingFrom LessWrong AI
Here's my rough impression of why people are researching personas despite RL seeming to shape much of the motivations and behaviour of the agents, c.f. Thoughts on the persona selection model (Sam Marks, 24th Sep 2026).I haven't bothered to check this with anyone.Anthropic: "We'll give Claude an aligned persona and hope massive RL doesn't completely burn through it."Owain Evans / TruthfulAI: "We'll study personas as part of a broader project of uncovering phenomena in LLM generalisation, which w
By Cleo Nardo