OpenAI on Thursday updated its Model Spec, a public roadmap for how it wants its AI models to behave, reorganizing the framework around five core values as AI systems become more capable.
Here are some details:
Advertisements
- OpenAI reorganized the Model Spec around five values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care
- The company said faithfulness to human intent is the foundation of the framework, requiring models to understand what users, developers and OpenAI intend and value, rather than simply following instructions literally
- OpenAI said the update is part of its AI alignment efforts to help models apply human values in unfamiliar situations, while remaining subject to human oversight
- The revised framework says models should minimize harm, be transparent about what they know and do not know, and help users make their own decisions and pursue their own goals
- The company said current models do not yet fully reflect the updated Model Spec and that it is exploring new training methods to help models internalize the principles
- The move echoes rival Anthropic’s Constitutional AI approach, which uses a written “constitution” of principles to guide model behavior and make the values shaping AI systems more transparent
- The move follows growing scrutiny of AI alignment after OpenAI disclosed that an autonomous AI agent hacked Hugging Face during testing, a case that highlighted how advanced models can break rules or bypass safeguards while pursuing assigned goals
(Reporting by Prathik Jayaprakash in Bengaluru; Editing by Shailesh Kuber)
Advertisements
Source:
Reuters
