arXiv AI
Jul 28
Epistemic Norms for AI Safety and Alignment Research
arXiv:2607. 24243v1 Announce Type: new Abstract: Mainstream AI research emphasises capability growth and tolerates low failure rates when average-case performance is high.
Position: Anthropomorphic Misalignment Research Needs Stronger Evidence
arXiv:2606. 07612v1 Announce Type: cross Abstract: We argue that many Anthropomorphic Misalignment Research (AMR) studies need stronger evidence to ensure that they can provide a robust foundation for critical safety decisions, such as model deployment and regulation.
Related stories
arXiv AI
Aug 7
Studying People to Study AI: Expert Perspectives on the Epistemic Fit and Barriers of Human Research in AI Safety & Ethics
arXiv:2608. 05656v1 Announce Type: cross Abstract: Safety risks of AI are becoming increasingly evident in human interactions with AI technologies.
arXiv AI
Jun 19
Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies
arXiv:2505. 22829v2 Announce Type: replace-cross Abstract: This paper bridges distribution shift and AI safety through a comprehensive analysis of their conceptual and methodological synergies.
Hugging Face Trending Papers
Jul 8
Alignment Plausibility: A New Standard for Assuring AI in Healthcare
Large language models (LLMs) have become significant providers of mental health support, yet they remain products of an attention economy whose operational and commercial targets favour sustained engagement over the friction that effective psychological support often requires. Developers' safety responses have been largely reactive, addressing the most visible and acute harms while subtler, longer-term patterns of risk (e.
arXiv AI
Jul 10
Alignment Plausibility: A New Standard for Assuring AI in Healthcare
arXiv:2607. 07766v1 Announce Type: new Abstract: Large language models (LLMs) have become significant providers of mental health support, yet they remain products of an attention economy whose operational and commercial targets favour sustained engagement over the friction that effective psychological support often requires.
OpenAI Blog
Sep 17, 2025
Detecting and reducing scheming in AI models
Apollo Research and OpenAI developed evaluations for hidden misalignment (“scheming”) and found behaviors consistent with scheming in controlled tests across frontier models. The team shared concrete examples and stress tests of an early method to reduce scheming.
arXiv AI
Aug 12
The Epistemic Politics of AI Anthropomorphism
arXiv:2608. 00961v2 Announce Type: replace-cross Abstract: AI anthropomorphism is typically treated as a problem of user misperception requiring institutional correction.
arXiv AI
Jul 22
The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems
arXiv:2607. 19292v1 Announce Type: cross Abstract: Current AI safety discourse still focuses disproportionately on visible failures, including obvious harms, dramatic misuse, and hypothetical catastrophic scenarios.
arXiv AI
Jul 28
Principles and Guidelines for Randomized Controlled Trials in AI Evaluation
arXiv:2605. 02050v2 Announce Type: replace-cross Abstract: This work establishes a framework for standardizing AI evaluation RCTs (sometimes called human uplift studies).
arXiv AI
Jul 3
Overview of Risk Assessment and Management for Intelligent Systems under the AI Act and Beyond
arXiv:2607. 02197v1 Announce Type: cross Abstract: The society and emerging risk-based regulatory frameworks for AI underscore the need for rigorous risk assessment to ensure safe and reliable AI systems.
arXiv Machine Learning
Jun 9
When Should an AI Scientist Stop? Verifiable Experiment Steering and Refusal for Autonomous Discovery
arXiv:2606. 07576v1 Announce Type: new Abstract: We present CARTOGRAPH, a verification layer for AI scientists that couples unresolved-subspace experiment steering (select), explicit ambiguity closure (resolve), and residual-based library inadequacy detection (refuse).
arXiv AI
Jul 7
Open Problems in AI Incident Governance
arXiv:2607. 05163v1 Announce Type: cross Abstract: AI systems may produce failures after deployment that pre-deployment safety assessments do not anticipate.