✨
AI Summary
- Subbarao Kambhampati studies planning and reasoning in AI systems, emphasizing how to build human-aware systems that can explain and justify their actions
- Examines interpretability challenges specific to large language models and proposes frameworks for ensuring AI systems remain aligned with human understanding and values
- Discusses the role of classical AI planning concepts in the era of LLMs, where reasoning transparency and human oversight remain crucial for trustworthy deployment