Do LLMs “think” in a similar way to humans? Or is it totally different?
Maybe it’s a good idea to listen to someone who publishes papers on this very subject, and is a professor of both philosophy and psychiatry and directs an Institute for Cognitive Science. That person is Dr. Chandra Sripada and his insights are fascinating.
Sean Carroll (interviewer, scientist and science communicator) says this interview made him lean towards the answer being “yes, they think like humans” whereas previously he favored the opposite view.
You can replace all the ‘reasoning’ steps from an LLMs output with “please wait” and it will still supply the same final answer. We think but LLMs just throw up connected bits of their training. Which was stolen from human reasoning in the first place. They are an illusion of thought at best and a malfunctioning search engine most of the time.
If you listened to the podcast (or were familiar with the literature) you’d know that’s simply Not True.
Sometimes, by listening to bona fide experts, you might learn new things instead of already knowing everything.
Model output can look like human reasoning however they often ignore these intermediate steps and the output tokens are often filler designed to allow more context to load. There something there that’s half way to reasoning because it’s loading that related training data but it not a connected chain of thought as we do. I read this article about it a few weeks ago and it summarizes the current research.
https://www.quantamagazine.org/is-ai-reasoning-right-for-the-wrong-reasons-20260731/
You should really listen to the podcast. Not going to summarize it here, but it looks like human reasoning including semantic activation patterns, use of productions, and dozens of other things that cognitive psychologists have known about for decades but for which they have not been able to come up with a mechanism.
Thanks that sounds interesting, will have a listen. Mapping human cognition to what’s likely represented with the stuff stored in neurons is very tricky but also quite intriguing.