IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures

The article discusses IatroBench, a newly developed framework that provides pre-registered evidence of iatrogenic harm resulting from AI safety measures. It highlights the potential unintended consequences of implementing safety protocols in AI systems, emphasizing the need for careful consideration in their design and deployment. This research aims to inform developers and policymakers about the risks associated with AI safety measures.