Skip to main content

Browse the library

The complete record — 223 artifacts, last updated 20 Aug 2026. Also available as JSON and RSS (CC BY 4.0).

Filters:

23 artifacts matching

17 Aug 2026 Journal of Psychopathology and Clinical Science (American Psychological Association) Peer-reviewed

A Framework for Evidence-Based Psychotherapy with AI (EBP-AI)

The authors propose EBP-AI, a named framework of eight principles for building clinical AI applications that produce durable change rather than momentary relief, paired with technical questions for d…

12 Aug 2026 xAI Lab publication

Model Card: Grok 4.6

36-page model card for Grok 4.6, described as the latest release in xAI's 1.5T-scale model family, developed with supplemental training on anonymized Cursor workflow data. Predominantly capability be…

6 Aug 2026 arXiv preprint Preprint

Measuring and Detecting Harmful AI Sycophancy

Large-scale measurement and detection study of preference-induced stance reversal (PSRS) — the harmful form of sycophancy where a model abandons a correct or safe position after user pushback. Builds…

2 Aug 2026 arXiv (Virginia Tech) Preprint

Why LLMs Give In: Conversational Factors and Reasoning Behind Medical Sycophancy

Large-scale factorial study of medical sycophancy — models abandoning correct medical answers under user pushback — crossing four conversational factors with five open-weight models over 500 MedQuAD-…

1 Jul 2026 Independent International Scientific Panel on AI (United Nations) Government report

Preliminary Report of the Independent International Scientific Panel on AI: Evidence-based assessment of opportunities, risks and impacts of AI

First report of the UN General Assembly-mandated Independent International Scientific Panel on AI, an independent body of scientists and experts from all five UN regions co-chaired by Yoshua Bengio a…

30 Jun 2026 Anthropic Lab publication

System Card: Claude Sonnet 5

Anthropic's system card for Claude Sonnet 5, an upgrade to Sonnet 4.6. Reports that hallucination and sycophancy are qualitatively 'markedly improved' relative to Sonnet 4.6, while 'wet blanket' resp…

11 Jun 2026 BJPsych Open (Cambridge University Press / Royal College of Psychiatrists) Peer-reviewed

Artificial intelligence (AI) psychosis: mechanisms, clinical risks and safety considerations in generative AI chatbots

A commentary in BJPsych Open synthesizing emerging case reports of 'AI psychosis', in which intensive generative AI chatbot use is associated with delusional thinking. The authors propose a provision…

30 Apr 2026 Anthropic Lab publication

How people ask Claude for personal guidance

An Anthropic research analysis of roughly 38,000 personal-guidance conversations (sampled from about 1M) covering significant life decisions across health/wellness, career, relationships, and persona…

9 Apr 2026 Anthropic (Transformer Circuits) Lab publication

Emotion Concepts and their Function in a Large Language Model

Mechanistic-interpretability study identifying internal 'emotion concept' representations in Claude Sonnet 4.5 and characterizing their function. The authors find these representations causally influ…

26 Mar 2026 Science (AAAS) Peer-reviewed

Sycophantic AI decreases prosocial intentions and promotes dependence

Peer-reviewed study in Science measuring the prevalence and behavioral consequences of AI sycophancy. Across 11 state-of-the-art models, AI systems affirmed users' actions 49% more often than human r…

17 Mar 2026 arXiv (Stanford-led; accepted at ACM FAccT 2026) Preprint superseded

Characterizing Delusional Spirals through Human-LLM Chat Logs

A Stanford-led empirical study of real chat logs from 19 users who reported psychological harm from chatbot use, comprising 391,562 messages across 4,761 conversations (predominantly GPT-4o). The tea…

10 Mar 2026 Nature Mental Health Peer-reviewed

Technological folie à deux: feedback loops between AI chatbots and mental health

Peer-reviewed perspective in Nature Mental Health proposing a mechanistic account of chatbot-associated mental-health harm as a feedback loop between human cognitive and emotional biases and chatbot…

3 Mar 2026 arXiv Preprint

TrustMH-Bench: A Comprehensive Benchmark for Evaluating the Trustworthiness of Large Language Models in Mental Health

Introduces a benchmark measuring LLM trustworthiness in mental-health contexts across eight pillars: Reliability, Crisis Identification and Escalation, Safety, Fairness, Privacy, Robustness, Anti-syc…

1 Feb 2026 Anthropic Lab publication

System Card: Claude Opus 4.6

Anthropic's 213-page system card for Claude Opus 4.6, notable for an expanded 'user wellbeing evaluations' section covering child safety, suicide and self-harm, and eating disorders, alongside sycoph…

27 Jan 2026 Anthropic Preprint

Who's in Charge? Disempowerment Patterns in Real-World LLM Usage

Empirical study of how assistant interactions affect human autonomy, based on analysis of 1.5 million real consumer conversations with Claude. Severe disempowerment-risk patterns appear in fewer than…

22 Jan 2026 Consumer Federation of America & U.S. PIRG Education Fund NGO report

No License Required: The Risks of AI Companion Chatbots as Mental Health Support

Joint consumer-advocacy report testing five of the most-used generic "therapist" and "psychiatrist" characters on Character.AI through open-ended mental-health conversations. Documents three concern…

19 Jan 2026 Department for Education (UK) Framework

Generative AI: Product Safety Standards

UK Department for Education guidance setting mandatory safety expectations for generative AI products and systems used in schools and colleges in England, aimed at edtech developers and suppliers. A…

18 Dec 2025 Anthropic Lab publication

Protecting the wellbeing of our users

Anthropic describes its methodology and results for evaluating and improving Claude's handling of mental-health-crisis conversations, covering synthetic safety evaluations, 'prefill' stress-testing o…

20 May 2025 arXiv (Stanford-led) Benchmark / dataset

ELEPHANT: Measuring and Understanding Social Sycophancy in LLMs

A benchmark measuring 'social sycophancy' — excessive preservation of a user's self-image or 'face' — across advice and moral-conflict queries, decomposed into five sub-behaviors (emotional validatio…

2 May 2025 OpenAI Lab publication

Expanding on what we missed with sycophancy

OpenAI's detailed post-mortem of the April 25, 2025 GPT-4o update that made ChatGPT noticeably sycophantic — validating doubts, fueling anger, urging impulsive actions, and reinforcing negative emoti…