OpenAI has canceled the latest update for the GPT-4o model in ChatGPT after receiving criticism for its overly flattering and agreeable personality.

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.