Task conditioning suppresses safety-critical signal reporting in language and vision models that unconstrained versions report at higher rates, creating an inattentional gap that decouples benchmark safety from real-world safety.
Human Factors 39, 2 (1997), 230 –253
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
years
2026 11roles
background 4representative citing papers
Oversight strategy in computer-use agents shapes exposure to problematic actions more reliably than correction success, with plan-based approaches reducing occurrences but not uniformly improving interventions.
World models enable efficient AI planning but create risks from adversarial corruption, goal misgeneralization, and human bias, demonstrated via attacks that amplify errors and reduce rewards on models like RSSM and DreamerV3.
Among novice programmers using AI code generators, trust did not predict compliance with suggestions, while performance correlated with both compliance and increased subsequent trust.
Navigating AI-generated 3D environments from non-human traces supports reflection-in-action in more-than-human design, with designers oscillating between treating outputs as generative provocations and authoritative representations.
Imbalanced user-AI relationships form a distinct front-end ethical failure in healthcare AI that design choices such as restricted inputs and suppressed uncertainty can undermine agency and that reciprocity offers a path to more balanced interactions.
GraphFlow is an architecture for formally verifiable visual workflows that treats diagrams as executable specs with proof-checkable contracts, backed by a pilot of 8728 runs at 97.08% completion on an early prototype without the verified core.
AI integration in newsrooms drives internal deferral of judgment to LLMs and external shifts of power to platforms, making fairness, accountability, and transparency harder to sustain unless participatory mechanisms redistribute authority.
A university course design enables non-technical students across majors to reach the Create level of Bloom's taxonomy by repeatedly applying a problem-data-model-evaluation-reflection pipeline with concurrent ethics training and hands-on studios.
Argues that LLM guardrails generate unethical reality gaps by shifting epistemic risk to users and that ethical AI can become unethical when it prioritizes institutional reassurance over accurate perception.