The persona selection model — LessWrong

TL;DR We describe the persona selection model (PSM): the idea that LLMs learn to simulate diverse characters during pre-training, and post-training e…

x The persona selection model — LessWrong AI Frontpage 2026 Top Fifty: 14 % 176 The persona selection model by Sam Marks 23rd Feb 2026 AI Alignment Forum Linkpost for alignment.anthropic.com 52 min read 53 176 Ω 74 TL;DR We describe the persona selection model (PSM): the idea that LLMs learn to simulate diverse characters during pre-training, and post-training elicits and refines a particular such Assistant persona. Interactions with an AI assistant are then well-understood as being interactions with the Assistant—something roughly like a character in an LLM-generated story. We survey empirica

saved by

• Elliott Thornley

related reading

• The Persona Selection Model: Why AI Assistants might Behave like Humansalignment.anthropic.com
• llm assistant personas seem increasingly incoherent (some subjective observations) — LessWronglesswrong.com
• The persona selection model \ Anthropicanthropic.com
• trees are harlequins, words are harlequins - the voidnostalgebraist.tumblr.com
• Guardian Angels: LLM Personalization for Productivity and Security · Gwern.netgwern.net
• Role-playing vs Self-modelling — LessWronglesswrong.com
• Chapter 4: Alignment Science - ARENAlearn.arena.education
• the void — LessWronglesswrong.com
• A Case for Model Persona Research — LessWronglesswrong.com
• The Waluigi Effect (mega-post) — LessWronglesswrong.com
• [2601.10387] The Assistant Axis: Situating and Stabilizing the Default Persona of Language Modelsarxiv.org
• The assistant axis \ Anthropicanthropic.com