Read news on Sycophancy with our app.
Read more in the app
OpenAI removes access to sycophancy-prone GPT-4o model
OpenAI removes access to sycophancy-prone ChatGPT-4o model
Sycophancy is the first LLM "dark pattern"
After GPT-4o backlash, researchers benchmark models on moral endorsement—find sycophancy persists across the board
Expanding on what we missed with sycophancy
OpenAI rolls back ChatGPT’s sycophancy and explains what went wrong
Sycophancy in GPT-4o
