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.
More from Models
- GLM-5.3-Flash runs 3.3x faster locally with Unsloth's 1-bit GGUFs on 100GB RAM — danielhanchen · 2026-09-04
- LFM2-350M NVFP4A16 hits 1.7M tok/s decode on a single RTX 5090 — AlpinDale · 2026-09-04
- A brief history of modern open source AI, from a Hugging Face early investor — Borthwick · 2026-09-04
- Hugging Face claims 18 million people use its open-weights models — flowersslop · 2026-09-04
- Google AI Pro at $5/mo vs GPT Plus vs OpenCode Go: a coder's comparison — Old-Dish-7104 · 2026-09-04
- World Model Week: Runway Solaris & GWM 2, World Labs Atlas, and OpenAI Astra 6 all land — Not Boring (Packy McCormick) · 2026-09-04