OpenAI Model Spec
2025-09-12 — OpenAI — OpenAI Website
Summary
Comprehensive behavioral specification defining intended behavior for OpenAI’s models, establishing a chain of command framework and detailed principles for safety, alignment, honesty, and appropriate model behavior across all deployment contexts.
Source
- Link: https://model-spec.openai.com/
- Listed in the Shallow Review of Technical AI Safety 2025 under 1 agenda(s):
- model-specs-and-constitutions — Black-box safety (understand and control current model behaviour) / Model psychology