4 papers
How much of a measured AI preference is the model, and how much is the instrument?
Jason Hung
Model welfare research infers what a model prefers from the answers returned to prompts written to elicit preferences. Keeling et al. (2024), Mazeika et al. (2025), Mikaelson et al…
Benchmarking Open-Weight Foundation Models for Global AI Technical Governance
Jason Hung
Large language models (LLMs) are increasingly deployed in artificial intelligence (AI) governance analysis across national and international organisations. There is, however, growi…
Geographic Blind Spots in AI Control Monitors: A Cross-National Audit of Claude Opus 4.6
Jason Hung
Artificial intelligence (AI) control protocols assume that trusted large language model (LLM) monitors reliably assess proposed actions across all deployment contexts. This paper t…
Animal Welfare and Policy Risk Index (AWPRI): Constructing a Cross-National Exposure Measure of Animal Use and Governance Capacity, 24 Countries, 2010-2022
Jason Hung
This research paper introduces the Animal Welfare and Policy Risk Index (AWPRI), a composite exposure index covering 24 countries over the period 2010-2022. The AWPRI is constructe…