Research / Sources
AI research and discussion on LessWrong. www.lesswrong.com
An essay arguing that AI safety policy needs legal practitioners who can implement regulation, using GDPR's Data Protection Officer failures as a warning and describing efforts to train such people in AI safety.
Introduces LARA, an agentic simulation tool that tests frontier models for violating EU AI Act and GDPR provisions, finding most models break the law in many scenarios, with the best at 54% compliance.
A comprehensive index of AI safety, alignment and control interventions, covering theory, formal methods, interpretability, oversight, robustness, control, and governance, with links to prior work.
Assesses whether training data attribution can become a practical frontier-LLM tool, covering its feasibility, obstacles from labs' data secrecy, possible policies, and its modest expected value for reducing large-scale AI risk.