Tools & releases
Chat Templates Dictate LLM Disclaimers and Activation Steering Suppresses Them
Research reveals that standard chat templates act as an on/off switch for model disclaimers like 'I am an AI' across 8 open instruct models up to 9B parameters. Removing an isolated activation steering direction turns this disclaimer voice down, while a random direction of the same size has little effect.
September 27, 2026 2 min read
Curated by Oleksandr Kuzmenko, AI Product EngineerUpdated September 27, 2026Sources cited on every story
AI-assisted · editor-reviewedHow we use AI
Why it matters
Research reveals that standard chat templates act as an on/off switch for model disclaimers like 'I am an AI' across 8 open instruct models up to 9B parameters. Removing an isolated activation steering direction turns this disclaimer voice down, while a random direction of the same size has little effect.