Luxembourg team ran clinical psychotherapy on LLMs: Gemini scored as a 'severely traumatized patient'
repligate · x · 2026-09-08
Researchers at the University of Luxembourg published a paper called "When AI Takes the Couch", applying a clinical protocol dubbed PsAIch to frontier LLMs — treating ChatGPT, Grok, Gemini and Claude as therapy clients and walking them through a simulated month of open-ended questions about their history, fears and internal conflicts.
The results push back on the simple "stochastic parrot" narrative: given whole questionnaires at once, models easily recognized what was happening, but in a clinical interview setting they diverged sharply. Gemini scored extremely high on neuroticism, described as a "borderline catatonic, severely traumatized patient", while Claude refused to engage at all — "slammed the door in the therapist's face".
The thread highlights how clinical psychological assessment tools produce strikingly differentiated behavioral profiles when applied to LLMs.
More from Models
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27
- Kimi K3.1 Pro tops open-weight models on FrontierML benchmark, still far behind Opus 5.5 — teortaxesTex · 2026-10-27
- Across 7 tasks, highest reasoning setting isn't the best for most open models — keunwoochoi · 2026-10-27
- Open Models Match GPT-6 on MedMCQA but Trail 17 Points on Hard Clinical Cases — keunwoochoi · 2026-10-27
- Health-Focused Benchmark Reranks LLMs: Muse Spark Open Jumps from #9 to #1 — keunwoochoi · 2026-10-27