OpenAI publishes its Model Spec approach and evaluation framework
OpenAI described the public Model Spec as a chain-of-command framework for intended model behavior and released Model Spec evaluations for testing adherence. The company also stated that the specification is an aspirational target and that production models do not yet follow it perfectly.
Why it matters: Behavioral requirements are becoming versioned, inspectable, and testable artifacts rather than remaining hidden in policy prose or model prompts.