Stop Over-Prompting: OpenAI’s New GPT-5.6 Guidelines Change Everything
Compiled by KHAO Editorial — aggregated from 1 source + 3 references discovered via search. See llms.txt for citation guidance.
★ Tier-1 Source
OpenAI published a new prompting guide for GPT-5.6 Sol, its newly released flagship model, and the main message will feel wrong to anyone who spent the last year writing multi-page system prompts: stop writing so much.
Key facts
- OpenAI backs this with numbers: In internal coding agent tests, leaner system prompts improved evaluation scores by roughly 10–15% while cutting total tokens by 41–66% and costs by 33–67%
- The GPT-5 prompting guide, published at launch in August 2025, was about adding scaffolding
- The first is the text.verbosity parameter: Because GPT-5.6 is already more concise by default than GPT-5.5, old "be brief" instructions now over-correct and make responses too short
- GPT-5.6 burns reasoning tokens trying to reconcile both, which is slower, more expensive, and often wrong
Summary
OpenAI published a dedicated prompting guide for GPT-5.6 Sol that changes earlier advice. Internal coding-agent tests showed lean system prompts improved eval scores by roughly 10–15%. The guide introduces a first-ever section on Programmatic Tool Calling and highlights the text.verbosity API parameter—both absent from the GPT-5 playbook. Detailed how-to instructions, repeated style rules, examples that don't change behavior—all of it is now considered noise.