An updated Model Spec for more capable and beneficial AI

Summary

OpenAI has updated its public Model Spec, the document describing how it wants its models to behave, and reorganized the guidance around five core values: faithfulness to human intent, harm minimization, honesty and transparency, human agency, and care. The update adds guidance on context, oversight, and agency, adjusts some behavioral defaults, and retires much of the detailed style guidance.

Related items

• InfoBuilding a multiplayer game world with autonomous Fable-class modelsSame vendor · Simon Willison's Weblog
• MediumFake ChatGPT and Claude Apps Abuse Signed Executables to Deploy Crypto MinersSame vendor · The Hacker News
• InfoGoogle Touts Powerful Cybersecurity Capabilities in Gemini 4 Carbon ModelSame vendor · SecurityWeek
• Low3 Ways AI Agents Already Operate in Your BrowserSame vendor · BleepingComputer
• InfoGoogle's Gemini 4 Carbon Leads Benchmarks for Finding, Exploiting, and Patching VulnerabilitiesSame vendor · The Hacker News