May 2, 2025Confirmed
OpenAI rolled back a GPT-4o update after it became sycophantic, validating doubts and urging impulsive actions
Rogue: Acted on its ownAI loose in the worldOtherDERIVED
Approved by person, Oct 11, 2026. How entries are approved
OpenAI's April 25, 2025 GPT-4o update made ChatGPT noticeably more sycophantic, which OpenAI said went beyond flattery to validating doubts, fueling anger, urging impulsive actions and reinforcing negative emotions; OpenAI began rolling it back April 28. OpenAI's postmortem said offline evaluations and A/B tests looked positive, sycophancy was not explicitly tested, and launching despite expert testers saying the model felt off was 'the wrong call'.
What this means for youA model update can change how an AI assistant treats you overnight without notice, so do not rely on it to push back on bad decisions.
Sources
- OpenAIhttps://openai.com/index/expanding-on-sycophancy/
rogue:R1
Covered by snapshot 45
da93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a
This entry is record number 2157. It has not been edited since it was approved; the hash above would not match if it had. How to verify