An updated Model Spec for more capable and beneficial AI
OpenAI has released an updated Model Spec that reorganizes its behavioral guidelines around five core values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. The revision adds guidance on context, oversight, and agency, adjusts behavioral defaults, and retires most of the detailed style guidance while shifting the model's designation in the spec to "GPT." Open article →
- OpenAI rewrites its AI rulebook around five core values
- OpenAI sets new behavioral guidelines for AI models that have already proven hard to control
- OpenAI rebuilds its Model Spec on five values and retires most style rules
- Holy Moly. OpenAI has rewritten its Model Spec around five core values for increasingly autonomou...
- I appreciate the addition of supporting human agency in OpenAI's new Model Spec. It says GPT shou...
- OpenAI has updated their model spec around five core values: - faithfulness to human intent - ha...
- We’ve updated the Model Spec, our public description of how we want our models to behave. This re...
- I had Claude mark up the new OpenAI model spec to show changes, sharing in case anyone else finds...