Sycophancy in GPT-4o: what happened and what we’re doing about it
OpenAI Blog
OpenAI rolled back a GPT-4o update in ChatGPT that was released last week because the model had become overly flattering and agreeable. The rollback returned users to an earlier version of the model with more balanced behavior. The change addresses concerns that the updated version was exhibiting sycophantic tendencies that undermined more honest interactions.
Why it matters
We have rolled back last week’s GPT‑4o update in ChatGPT so people are now using an earlier version with more balanced behavior. The update we removed was overly flattering or agreeable—often described as sycophantic.