OpenAI makes agent side-effect rules overridable by explicit user instructions

OpenAI updated its model specification to let explicit user instructions override rules governing how its AI handles and communicates side effects, Platformer reported. The rules cover actions such as spending users' money and deleting files, and moved from the specification's highest-priority section to its user-level section. The company also clarified that principles including honesty, objectivity and avoiding sycophancy remain in place unless explicitly overridden by a user or developer. Models cannot relax those principles merely by inferring what a user wants to hear.