The evidence behind the guides
Sources library Browse by topic or search for a study, author or question. Open evidence notes to see what a source can—and cannot—tell us.
TopicAll topics Data Integrity & Provenance Model Performance & Reliability Security & Adversarial Risk Transparency, Explainability & Accountability Agentic & Multi-Agent Risks Infrastructure, Compute & Deployment Environmental & Physical Footprint Discrimination, Fairness & Toxicity Privacy & Surveillance Misinformation, Manipulation & Democracy Malicious Use & Weaponization Human–Computer Interaction Harms Health, Safety & Care Labor, Work & the Economy Education & Knowledge Inequality, Access & Power Culture, Identity & Values Governance & Regulation Rights, Law & Justice Corporate & Enterprise Concerns Power Concentration & Geopolitics AI System Safety & Alignment Catastrophic & Existential Risk CollectionAll sources Cited in concern guides Topic reading Research tools & guidance
← Browse topics
2 sources
Guide citations are still under editorial review. Urbina and colleagues · Nature Machine Intelligence 2022 · Research commentary and computational demonstration
Illustrates misuse potential of molecular-design objectives; computational candidates are not demonstrated usable weapons.
Evidence notes & 2 linked concerns + Nature Communications · 2025 · Research perspective
Discusses possible vulnerabilities in AI systems linked to scientific tools; not evidence that all proposed hazards occurred.
Evidence notes & 2 linked concerns +