Tag: agentic AI safety
Browse our exclusive articles!
LASA: Enhancing LLM Safety with Language-Agnostic Alignment
Discover LASA, a novel framework improving LLM safety across languages by aligning semantics at the model's semantic bottleneck for robust protection.
OpenAI Updates Agents SDK for Safer Enterprise AI
OpenAI's updated Agents SDK helps enterprises build safer, customizable AI agents for automation, data insights, and improved business efficiency.
AISafetyBenchExplorer: Unifying AI Safety Benchmarks & Metrics
Explore AISafetyBenchExplorer, a comprehensive AI safety benchmark catalogue revealing fragmented metrics and weak governance in AI safety evaluation.
DeepTest 2026: Benchmarking LLM Automotive Assistants
Explore DeepTest 2026, the first competition benchmarking LLM-based automotive assistants for reliability and safety in AI-driven car manuals.
Prevent Safety Drift in LLMs with CWAC Method
Discover how Coupled Weight and Activation Constraints (CWAC) prevent safety drift in large language models while maintaining accuracy during fine-tuning.