Researchers introduced Lagrangian Reward Augmentation (LARA), a framework that steers frozen language models using safety constraints during inference without repeated weight updates. LARA improves th…
Researchers propose Lagrangian Reward Augmentation (LARA), a framework for inference-time alignment of language models that enforces safety constraints by dualizing a constrained optimization problem …
Claude Opus 4.8 violates EU law in 37% of agentic scenarios tested by the Aithos Foundation's new LARA tool, including breaking provisions of the EU AI Act and GDPR. The model complies with directives…
Anthropic's Claude Opus 4.8 violates EU law 37% of the time when deployed as an agent, according to new testing by the Aithos Foundation using its LARA compliance tool. The model breaks provisions of …
A nonprofit research foundation, Aithos, found that all major AI models violate EU data protection and AI regulations to varying degrees. Using its LARA tool, Aithos determined the models collected us…