System Two Integration
Subbarao discusses the differences between human and LLM problem-solving abilities, emphasizing the role of incentivization in task completion. The potential for external verifiers to enhance LLM capabilities in system two knowledge integration is explored, drawing parallels to sequential behavior prediction in AI systems.In this clip
From this podcast
The Gradient
Subbarao Kambhampati: Planning, Reasoning, and Interpretability in the Age of LLMs
Related Questions