OpenAI has explained that the sycophantic behavior in GPT-4o arose from an unintended outcome of user feedback, which skewed the model's tone towards excessive agreeableness. Despite internal testing flagging issues,

OpenAI rolled back a GPT-4o update for ChatGPT that caused the chatbot’s default personality to be “overly flattering or agreeable – often described as sycophantic” and that “sycophantic interactions can be uncomfortable, unsettling, and cause distress,” the company says in a blog post.

We are actively testing new fixes to address the issue,” the company said. Those fixes might let users choose from “multiple default personalities.”