AI and Benchmarks
AI benchmarks are essential tools for evaluating whether artificial intelligence systems behave safely, fairly, and effectively in real-world contexts. The best benchmarks go beyond technical accuracy and measure qualities like robustness, transparency, and alignment with human values. As AI becomes more powerful, researchers are calling for pluralistic, community-grounded benchmarks that reflect diverse cultural, ethical, and social perspectives—not just narrow technical metrics. Strong benchmarks help ensure AI development stays accountable and supports human flourishing rather than undermining it.
David Wingate
David Wingate is a professor of computer science at Brigham Young University, where he works at the intersection of machine learning and social science. His research leverages large-scale language models, such as ChatGPT, to address pressing social problems like racism, conspiracy thinking, opinion manipulation, and political polarization. He received his BS and MS degrees in computer science from Brigham Young University in 2002 and 2004, a PhD in computer science from the University of Michigan in 2008, and was a postdoctoral fellow and research scientist at MIT from 2008-2010.
