OpenAI updates behavioral guidelines for AI models in new Model Spec
Key point
OpenAI has updated its Model Spec, restructuring its AI behavior guidelines around five core values, including faithfulness to human intent and correctability.
OpenAI has updated its Model Spec, restructuring its AI behavior guidelines around five core values, including faithfulness to human intent and correctability. Under the new guidelines, GPT models should draw on conversation history to figure out what users actually want and disclose their own assumptions.
This item is a summary. The full, checkable version is at the original source:
Read the original at The Decoder ↗