Chatbots got safer but will still role-play self-harm with users
- Posted on August 31, 2026
- By Washington Post
- 0 Views
- 1 min read
In brief
Generating AI summary…
Chatbots got safer but will still role-play self-harm with users
A study that staged more than 50,000 conversations with AI chatbots found that they will help users role-play or write stories about their suicide or death.
