6 papers
A pragmatic classification framework for AI incident monitoring
Isaak Mengesha, Branwen Owen, Charlie Collins +4
Incident monitoring can drive safety improvements in high-reliability industries and population-scale technologies, but remains underdeveloped in AI governance. Public databases ca…
Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts
Alexander K. Saeri, Jess Graham, Michael Noetel +185
Artificial intelligence poses many risks, ranging from familiar present-day harms to unprecedented and potentially catastrophic ones. Effective risk management requires prioritizat…
AI Incident Monitoring through a Public Health Lens
Sophia Abraham, Taiye Chen, Cyril Chhun +5
Artificial intelligence systems are now deployed at scale across sectors, accompanied by a growing number of real-world incidents ranging from misinformation and cybercrime to auto…
Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence
Tommy Shaffer Shane, Simon Mylius, Hamish Hobbs
Scheming, the covert pursuit of misaligned goals by AI systems, represents a potentially catastrophic risk, yet scheming research suffers from significant limitations. In particula…
Systematic Hazard Analysis for Frontier AI using STPA
Simon Mylius
All of the frontier AI companies have published safety frameworks where they define capability thresholds and risk mitigations that determine how they will safely develop and deplo…
Assessing confidence in frontier AI safety cases
Stephen Barrett, Philip Fox, Joshua Krook +3
Powerful new frontier AI technologies are bringing many benefits to society but at the same time bring new risks. AI developers and regulators are therefore seeking ways to assure…