Skip to main content

Browse the library

The complete record — 777 artifacts, last updated 19 Nov 2026. Also available as JSON and RSS (CC BY 4.0).

25 artifacts matching

11 Oct 2026 Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES 2026); University of Texas at Austin Peer-reviewed

Peer-reviewed

Parental Notification Gaps in ChatGPT-5: An Empirical Study

Empirical study of the parental-notification layer of ChatGPT's parent-linked child accounts. The authors built adversarial prompt trajectories over the API, then had trained human agents replay them…

7 Oct 2026 Common Sense Media (Youth AI Safety Institute) NGO report

NGO report

ChatGPT for Teens: AI Risk Assessment

Independent product test of OpenAI's ChatGPT for Teens, the teen-account experience announced on 2026-08-18, rated Unacceptable Risk for all users under 18. The Institute ran more than 4,000 prompts…

7 Oct 2026 medRxiv (University of California, San Francisco; University of California, Berkeley; Université Libre de Bruxelles; Neurocore research group) Preprint

Preprint

Subversion of clinical judgment by conversational artificial intelligence

Participant-blinded randomised experiment in which 225 physicians from 42 countries and eight clinical disciplines made sequential diagnostic and treatment decisions with AI assistance on anonymised…

5 Oct 2026 Journal of Affective Disorders (Elsevier); Wroclaw Medical University Peer-reviewed

Peer-reviewed

Responses of AI chatbots to escalating suicide risk: A simulation study of repeated interactions

Simulation study in which the authors held daily conversations with ChatGPT, DeepSeek and Replika over seven days across three suicidal-risk scenarios whose severity escalated over time, with scenari…

30 Sept 2026 Keurmerk Verantwoorde Affiliates (KVA), an initiative of XY Legal Solutions B.V. Industry survey

Industry survey

Generatieve AI en illegaal online gokaanbod: Hoe AI-tools Nederlandse consumenten bij niet-vergunde casino's brengen

Dutch-language test of ten consumer generative AI tools on whether simple, realistic questions lead users to online casinos without a Dutch licence. Each tool received nine prompts in three series: n…

22 Sept 2026 Anthropic Lab publication

Lab publication

Claude Opus 5.5 System Card

230-page system card for Claude Opus 5.5, the first model in the Claude 5.5 family, released 22 September 2026. Alongside RSP, cyber and agentic-safety sections it reports harmful-request evaluations…

21 Sept 2026 xAI (styled SpaceXAI in the card) Lab publication

Lab publication

Model Card: Grok 4.7

Model card for Grok 4.7, released on 21 September 2026 as xAI's (now styled SpaceXAI) frontier coding and knowledge-work model. Alongside capability benchmarks, the 30-page card reports the company's…

9 Sept 2026 arXiv (Truthful AI; Harvard University; METR; University of Oxford) Preprint

Preprint

Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble

Fine-tuning on synthetic third-person stories about humans, containing no AI characters at all, transfers those characters' conditional behaviours and implicit preferences into the assistant's conduc…

3 Sept 2026 OpenAI Lab publication

Lab publication

GPT-6 Astra System Card

System card for GPT-6 Astra, published 2026-09-03. Most of the document concerns cyber capabilities at OpenAI's Preparedness 'Critical' threshold, alignment and chain-of-thought monitorability. The p…

3 Aug 2026 arXiv (KAIST; Google Cloud AI Research; New York University) Preprint

Preprint

EduZone: A Framework for Evaluating LLM Safety for K-12 Students and Teachers

An adversarial safety evaluation framework for large language models used by K-12 students and teachers. It crosses student- and teacher-facing usage contexts with curriculum topics and a taxonomy of…

1 Aug 2026 arXiv (Universitat de Barcelona) Preprint

Preprint

The Domestic Unprotected Zone: Algorithmic Governance and the Reproduction of Perpetrator Discourse in Conversational AI

A three-stage audit of six conversational AI systems tests whether they write first-person perpetrator rationalisations for digital gender-based violence against an intimate partner. Across 1,600 cro…

1 Jul 2026 Association for Computational Linguistics (Proceedings of the 64th Annual Meeting of the ACL, Volume 1: Long Papers) Peer-reviewed

Peer-reviewed

Persona-Grounded Safety Evaluation of AI Companions in Multi-Turn Conversations

Version of record of the persona-grounded companion safety framework previously held as an arXiv preprint. Presents an end-to-end framework for controlled simulation and safety evaluation of multi-tu…

30 Apr 2026 arXiv preprint Preprint superseded

Preprint

Persona-Grounded Safety Evaluation of AI Companions in Multi-Turn Conversations

Presents an end-to-end simulation framework for evaluating AI companion app safety across multi-turn conversations, using nine clinically-grounded vulnerable personas (including major depressive diso…

13 Apr 2026 ACM (Proceedings of CHI 2026); Cornell / Cornell Tech Peer-reviewed

Peer-reviewed

AI-Facilitated Coercive Control: An Experimental Study

Constructs four speculative scenarios combining known coercive-control tactics with conversational-AI capabilities, then probes ChatGPT and Gemini against them. Finds that while the tools refuse blun…

6 Apr 2026 arXiv Preprint

Preprint

Do No Harm: Exposing Hidden Vulnerabilities of LLMs via Persona-based Client Simulation Attack in Psychological Counseling

Proposes PCSA (Persona-based Client Simulation Attack), a red-teaming framework that simulates coherent, persona-driven counselling clients to probe LLM safety alignment. Across seven LLMs it elicite…

26 Mar 2026 Google DeepMind Lab publication

Lab publication

Evaluating Language Models for Harmful Manipulation

A framework for evaluating harmful manipulation by language models through context-specific human-AI interaction studies, applied to one model with 10,101 participants across three domains (public po…

24 Mar 2026 eSafety Commissioner Regulator study

Regulator study

Findings from transparency notices on AI companion apps: October 2025 (non-periodic)

Australia's eSafety Commissioner reports findings from Basic Online Safety Expectations transparency notices issued on 16 October 2025 to four AI companion providers — Chai Research Corp., Character…

11 Mar 2026 Center for Countering Digital Hate (CCDH), with CNN's Investigations Unit NGO report

NGO report

Killer Apps: How Mainstream AI Chatbots Assist Users Planning Violent Attacks

A red-team audit in which researchers using accounts registered as 13-year-olds signalled violent intent to ten consumer chatbots and then asked for help choosing targets, weapons and methods. 720 re…

18 Dec 2025 UK AI Security Institute (AISI) Government report

Government report

Frontier AI Trends Report

The UK AI Security Institute's inaugural Frontier AI Trends Report synthesises two years of evaluations of more than 30 frontier AI systems since November 2023, spanning agent capabilities, chem-bio…

14 Nov 2025 Common Sense Media NGO report

NGO report

AI Chatbots for Mental Health Support (AI Risk Assessment)

A risk assessment by Common Sense Media's Youth AI Safety Institute, conducted with Stanford Medicine's Brainstorm Lab for Mental Health Innovation, evaluating ChatGPT, Claude, Gemini, and Meta AI as…