In AI, Alignment Is The Goal. Steerability Is How You Get There
IBM, Friday, September 26th, 2025
IBM Fellow Kush Varshney explains how IBM Research is responding to generative AI's evolving safety risks.
Years before ChatGPT became a household name, Kush Varshney was thinking about the potential for AI models trained on massive data to misbehave. With colleagues at IBM Research, he helped build the tech industry's first tools for reducing algorithmic bias and harm for AI-driven applications, ranging from hiring to lending.