What AI gets wrong and what failure teaches us
Jennifer Neville discusses her research into "surprising failures" in AI systems, where models, particularly LLMs, struggle with complexity in realistic user workflows. Her team focuses on practical evaluation for multi-turn conversations and agentic knowledge work, emphasizing the need for robust AI that understands context and user intent over time. She offers insights into bridging the gap between user expectations and AI capabilities, advocating for detailed user feedback and outlining the future of human-AI collaboration.
Jennifer Neville, a partner research manager at Microsoft Research and professor at Purdue, shares her non-linear path into computer science and AI, and discusses her team’s work on understanding and mitigating “surprising failures” in AI systems, particularly large language models (LLMs), within complex, interactive environments.
Jennifer Neville’s Journey to AI Research
Neville’s career began with an initial aversion to computer science, influenced by her father’s profession. She explored mathematics, physics, and cognitive science before serendipitously discovering AI while seeking to work with data. Her