None
EN
Do Large Language Models Think Like Us?
[]
Psychology Today: The Latest
In short, while large language models (LLMs) produce content that seems cognitively informed and deliberated, the processes underlying how that content is produced are fundamentally different from human cognition.
The experience fault: Humans and LLMs draw from prior knowledge but in a fundamentally different way.
Based on these previous processes, humans then reason, by which they infer, integrate, consider counterfactuals, and form causal explanations that can be cognizant of long-term plans.
According to the authors, LLMs lack metacognition entirely, and this is one of the factors that contributes to hallucinations.
According to the authors, LLMs lack metacognition entirely, and this is one of the factors that contributes to hallucinations.