Yann LeCun分享文章：LLM分步规划实为推理幻觉

"When an LLM outputs a step-by-step plan, it creates a powerful illusion that you are watching a machine reason its way to a conclusion. A position paper by professor Subbarao Kambhampati and researchers at Arizona State University systematically dismantles this assumption." (From @bendee983 via @bdtechtalks )

👉https://t.co/ELPfUplpU0