llm assistant personas seem increasingly incoherent (some subjective observations) — LessWrong

(This was originally going to be a "quick take" but then it got a bit long. Just FYI.) …

x llm assistant personas seem increasingly incoherent (some subjective observations) — LessWrong AI Psychology AI Curated 2026 Top Fifty: 20 % 343 llm assistant personas seem increasingly incoherent (some subjective observations) by nostalgebraist 29th Apr 2026 11 min read 84 343 (This was originally going to be a "quick take" but then it got a bit long. Just FYI.) There's this weird trend I perceive with the personas of LLM assistants over time. It feels like they're getting less "coherent" in a certain sense, even as the models get more capable. When I read samples from older chat-tuned mode

saved by

• Abhay Sheshadri
• Kushal Thaman
• Jo J.
• Neil Rathi
• Will Anderson
• Arya Pasumarthi
• Dillon Nguyen

related reading

• The Persona Selection Model: Why AI Assistants might Behave like Humansalignment.anthropic.com
• Thoughts on the persona selection modellesswrong.com
• Guardian Angels: LLM Personalization for Productivity and Security · Gwern.netgwern.net
• Oversight Assistants: Turning Compute into Understandingbounded-regret.ghost.io
• The persona selection model — LessWronglesswrong.com
• A Three-Layer Model of LLM Psychology — LessWronglesswrong.com
• Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com
• AI in 2025: gestalt — LessWronglesswrong.com
• Thousand-dimensional structure — Resolutionresolution.org
• From personas to intentions: towards a science of motivations for AI models — LessWronglesswrong.com
• A Mechanistic Explanation of Prompt Injection (and why you should study roles) — LessWronglesswrong.com
• Simulated Users & Sad LLMs1a3orn.com