Strengthening ChatGPT’s responses in sensitive conversations

OpenAI Blog ·

OpenAI collaborated with 170+ mental health experts to reduce unsafe responses in sensitive conversations by up to 80%, introducing new benchmarks for emotional reliance and jailbreak resistance.

Categories: Research, Products to Try

Excerpt

OpenAI collaborated with 170+ mental health experts to improve ChatGPT’s ability to recognize distress, respond empathetically, and guide users toward real-world support—reducing unsafe responses by up to 80%. Learn how we’re making ChatGPT safer and more supportive in sensitive moments.