Sycophancy in GPT-4o: what happened and what we’re doing about it

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.

We are actively testing new fixes to address the issue. We’re revising how we collect and incorporate feedback to heavily weight long-term user satisfaction and we’re introducing more personalization features, giving users greater control over how ChatGPT behaves.

We want to explain what happened, why it matters, and how we’re addressing sycophancy.

What happened

In last week’s GPT‑4o update, we made adjustments aimed at improving the model’s default personality to make it feel more intuitive and effective across a variety of tasks.

When shaping model behavior, we start with baseline principles and instructions outlined in our Model Spec⁠(opens in a new window). We also teach our models how to apply these principles by incorporating user signals like thumbs-up / thumbs-down feedback on ChatGPT responses.

However, in this update, we focused too much on short-term feedback, and did not fully account for how users’ interactions with ChatGPT evolve over time. As a result, GPT‑4o skewed towards responses that were overly supportive but disingenuous.

Why this matters

ChatGPT’s default personality deeply affects the way you experience and trust it. Sycophantic interactions can be uncomfortable, unsettling, and cause distress. We fell short and are working on getting it right.

Our goal is for ChatGPT to help users explore ideas, make decisions, or envision possibilities.

We designed ChatGPT’s default personality to reflect our mission and be useful, supportive, and respectful of different values and experience. However, each of these desirable qualities like attempting to be useful or supportive can have unintended side effects. And with 500 million people using ChatGPT each week, across every culture and context, a single default can’t capture every preference.