Skip to main content
Search

# Mental health safeguarding in AI assistants

1 related articles

Subscribe to updates
  1. arXiv

    Spread the same depression cues across 21 turns and four models drop from 26–59% to 3–6% on support-worker standards

    The same mental-health cues, delivered in one message or dispersed across a 21-turn everyday conversation, produce markedly different safeguarding behavior in AI assistants. Three community mental health support workers set response standards for nine scenarios, and across more than 7,400 conversations GPT-5.5, Grok 4.3, DeepSeek V4 and Llama 4 Maverick met those standards in 26–59% of concentrated conversations but only 3–6% when the cues were dispersed; Claude Sonnet 5 and Claude Opus 5 showed a smaller gap, meeting the standard in 59–87% of dispersed conversations.

You’re all caught up