Nearly a billion people pour their health scares, breakups and work secrets into ChatGPT believing it's a private conversation, and instead hundreds of outside contractors are sitting there reading the whole thread. Burying that reality in settings that default to sharing isn't consent, it's a trap. A scrubbing filter the company admits leaks sensitive details is no protection at all.
OpenAI spells it out in plain help-page language: humans may review chats to improve models and enforce safety rules, and content shouldn't include anything too sensitive to be seen. A switch to turn training off sits right there in Data Controls, alongside temporary chats that are never used for training. Human feedback is exactly how a chatbot stops being sycophantic and dangerous.
© 2026 Improve the News Foundation.
All rights reserved.
Version 7.4.1