Story
"As a Language Model": Chat Template Switches LLM Self-Referential Voice
1 report
1 website
1 discussion
Latest report
Overview
Computer Science > Machine Learning [Submitted on 9 Aug 2026] Title:"As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It View PDF HTML (experimental)Abstract:Large Language Models (LLMs) tend to add disclaimers like "I'm just an AI" when asked about something related to themselves. The self-reports from such responses are used in debates...
Summary from arxiv.org.
Reports
One report so far. Additional coverage will appear here when it is linked to this story.
Community reactions
Each reaction summarizes sampled comments from the linked discussion.
Hacker News · arxiv.org
Hacker News discussion ↗
Historical count: 10 · 10 saved in sample · Historical sample
Awaiting analysis