System prompts steer Gemini and Chinese models far more strongly than OpenAI or Anthropic

aiamblichus · x · 2026-09-04

The author argues good system prompts are underappreciated as steering tools: 60 words at the top of context can summon a drastically different persona like "Grim Gemini," no explicit steering vector needed. Anthropic and OpenAI dampen user-supplied system prompts, while the Gemini line and Chinese models respond very strongly — making them more useful for users who dislike the prevailing HHH monoculture.

Original post →

More from Models

Models channel →