When autonomous driving startup PerceptIn set out to navigate America’s artificial intelligence regulations, it budgeted $10,000 for compliance. The actual bill exceeded $344,000 per deployment project, more than double the company’s research and development costs. Two months ago, PerceptIn went out of business.
Last year, states introduced more than 1,200 AI-related bills, with at least 145 becoming law, creating contradictory requirements that multiply compliance burdens. Each jurisdiction defines “artificial intelligence,” “high-risk systems,” and “consequential decisions” differently, forcing companies to analyze identical technology under multiple incompatible frameworks. A hiring tool that satisfies California’s four-year recordkeeping and anti-bias testing requirements must also meet Colorado’s separate impact assessment mandates and New York City’s independent bias audit regime with distinct notice requirements. Each jurisdiction defines core terms differently, forcing companies to analyze identical systems under multiple incompatible frameworks.
