Research / Sources
AI research and discussion on LessWrong. www.lesswrong.com
A policy-oriented overview arguing AI safety receives tiny resources relative to capabilities and that current alignment techniques, evaluations and guaranteed-safe approaches fall short for AGI/ASI.
Empirical null result: behavioral tests on Hughes et al.'s open-source Llama 70B checkpoints found no strict alignment faking, so the planned probe generalization test could not be run.
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.