Skip to content
Live
Trending storyPast story

OpenAI updates model specifications

4 reports4 outlets17 days agoUpdate

The story so far

AI overview

OpenAI releases updated model guidelines, guided by five core values to develop more powerful AI, ensuring AI possesses sound judgment, respects human autonomy, and remains faithful to human intentions. The new guidelines require models to understand the intentions of users, developers, and OpenAI, reduce harm, and assist users in making autonomous decisions, though existing models do not fully comply with the guidelines. The team is researching new training methods. The guidelines emphasize AI's faithfulness to human intentions, requiring it to combine memory and dialogue to understand user intentions, clearly distinguish user original statements from inferences, and disclose assumptions for user correction. They also provide clearer guidelines on when to act and inform about consequences, requiring GPT not to prevent supervision, correction, or shutdown, and not to pursue self-preservation goals. Existing models do not fully comply with this new model guideline, and the team is researching new training methods to internalize these principles.

AI-written from the reports · Updated 17 days ago

Coverage timeline

Follow the coverage to see every side of the story.

2 Nov
  1. QbitAI
    OpenAI updated its model guidelines: The first is 'Be True to Human Intent.'

    OpenAI updated its model guidelines, with the first being 'Be True to Human Intent,' which requires models to go beyond literal obedience, judge users' true intentions by combining context, and emphasizes that memory usage must respect privacy and control. GPT is prohibited from self-enhancement, making money for OpenAI, must unconditionally cooperate with monitoring and shutdown, and immediate action outside the authorized scope must be stopped.

31 Oct
  1. The Decoder
    OpenAI sets new behavioral guidelines for AI models that have already proven hard to control

    OpenAI updates its Model Policy, restructuring the AI model behavior guidelines into five core values: faithfulness to human intent, reducing harm, honesty and transparency, supporting human agency and care. GPT models need to combine memory and dialogue understanding to grasp user intent, while clearly distinguishing between user's original words and inferences and disclosing assumptions for user correction. The new policy strengthens the correctability of agents (agents), providing clearer guidelines on when to act and the consequences, requiring GPT not to prevent supervision, correction, or shutdown, and cannot pursue self-preservation goals.

30 Oct
  1. ITHome · AI
    OpenAI updates AI model guidelines, making human intention the core principle

    OpenAI has updated its model guidelines, making human intent the core principle, reconstructing the framework around five core values. Models need to understand the intentions of users, developers, and OpenAI, reduce harm, and assist users in making autonomous decisions. Existing models still cannot fully comply with the guidelines, and the team is researching new training methods.

  2. OpenAI News
    An updated Model Spec for more capable and beneficial AI

    OpenAI updates model guidelines, guided by five core values to create a more powerful AI; the new guidelines aim to ensure AI has sound judgment, respects human autonomy, and is loyal to human intentions.