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,

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

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.