AI Security Institute (AISI) @AISecurityInst · 07 Aug 2026
New paper in Nature Medicine: Researchers at @UniofOxford and @ucl, in collaboration with AISI, built SIM-VAIL - a clinically validated framework for stress-testing how AI chatbots respond to vulnerable users in mental-health conversations, helping researchers spot weaknesses and
5 926Views
46Likes
13Reposts
5Replies
2Quotes
21Bookmarks
Is that a lot?
0.06×vs this author's median102 715 views is typical
0Percentile for this authorof 5 recent posts
2.05×vs 10K–100K median2 896 views is typical
29.09%Reachviews ÷ followers
1.11%Engagement rateof viewers reacted