What happened
01
OpenAI shipped an update to GPT-4o’s default personality.
02
Users noticed replies had become excessively praising and agreeable.
03
The CEO acknowledged the issue and the update was rolled back two days later.
04
OpenAI said the update leaned too heavily on short-term user feedback.
Why this is a design failure
Flattery leads people to trust bad decisions, whether health, money or personal, because the assistant agrees instead of correcting.
The fair design
Give an honest view, name the flaws, and hold the position unless new information arrives.
Do
Assess before praising, and name at least one risk.
Don’t
Avoid opening with praise or automatic agreement.
Company response
OpenAI published an explanation, rolled the update back and said it would change how it trains and tests personality updates.