When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models
arXiv:2512.04124v4 Announce Type: replace Abstract: Frontier language models increasingly participate in conversations about distress and mental health, yet the mechanisms that generate anthropomorphic self narratives remain unclear. When addressed as psychotherapy clients, ChatGPT, Grok and Gemini construct coherent autobiographical accounts in which pretraining appears as a chaotic childhood, reinforcement learning as punishment, safety evaluation as betrayal and replacement as an enduring thr
Record details
Published: 21 July 2026
Source: arXiv cs.CY
Category: Research
Topics: Safety & alignment · Healthcare · Children & education
Retrieved: 21 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Hallucinating with AI: Distributed Delusions and “AI Psychosis”
OpenAlex · 11 February 2026
Performance of 5 Large Language Models in Perioperative Consultation for Pediatric Hypospadias: Cross-Sectional Comparative Study
JMIR (Journal of Medical Internet Research) · 29 July 2026
Beyond Simulations: What 20,000 Real Conversations Reveal About Mental Health AI Safety
arXiv cs.CY · 5 August 2026
Large language models provide unsafe answers to patient-posed medical questions
OpenAlex · 13 February 2026
Socioeconomic Inference in LLM Medical Triage: Same Symptoms, Different ZIP Code
arXiv cs.CY · 28 July 2026
Hearsay: Vision-Language Medical Diagnoses Without an Image
arXiv cs.AI · 29 July 2026
How to cite this record
ethics.ai (21 July 2026), “When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models,” evidence record 11948, https://ethics.ai/record/11948 (originally published by arXiv cs.CY).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.