These improvements build on years of extensive work⁠ across model training, evaluations, monitoring systems, and more than two years of collaboration with mental health and safety experts.

In sensitive conversations, context can matter as much as a single message. A request that appears ordinary or ambiguous on its own may carry a very different meaning when viewed alongside earlier signs of distress or possible harmful intent. To respond appropriately, we train ChatGPT to recognize the potential harmful intent from the surrounding context so that it can refuse the request, de-escalate, and guide the user toward support.

These cases are uncommon, but critically important to get right. Our goal is to help ChatGPT connect relevant signals when they matter without overreacting in ordinary conversations.

We focused this work on acute scenarios including suicide, self-harm, and harm-to-others. Working with mental health experts, we updated our model policies and training to improve ChatGPT’s ability to recognize warning signs that emerge over the course of a conversation and use that context to inform more careful responses.