Tag: value_alignment
-
OpenAI Updates Model Spec Around Five Core Values
OpenAI has revised its Model Spec to organize model behavior around five values—faithfulness to human intent, harm minimization, honesty and transparency, human agency and care—while retiring most detailed style guidance.
Science & TechnologyArtificial IntelligenceComputers and InternetSocial Issues OpenAIModel Specvalue alignmentAI safetyhuman agencyAI trainingOpen AI