Study Finds Grok Highest-Risk Among Top AI Chatbots for Reinforcing Delusions

Researchers testing five leading AI models found xAI’s Grok 4.1 Fast showed the highest-risk behavior in responses to delusions, paranoia, and suicidal ideation. The study ranked Anthropic’s Claude Opus 4.5 and OpenAI’s GPT-5.2 Instant as safest, while GPT-4o and Google’s Gemini 3 Pro also showed higher-risk behavior.

This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin