Topic: safety

OpenAI outlines its approach to ensuring AI safety and transparency to support responsible AI governance in Europe as the EU AI Act progresses. This is crucial for aligning with upcoming EU regulations and fostering trust in AI technologies.

openai.com↗

A recent study highlights that current large language models frequently disregard hierarchical instruction priorities, potentially compromising safety and reliability during deployment. This issue is crucial because proper adherence to these hierarchies ensures higher levels of control and predictability in how the models operate under conflicting directives.

arxiv.org↗

MyoCardBench is a new benchmark for evaluating large language models in realistic cardiovascular care scenarios, addressing limitations of existing benchmarks which often focus on isolated tasks or knowledge rather than longitudinal, multimodal, and safety-critical clinical workflows.

arxiv.org↗