Humans have the cognitive capacity to infer and reason about the minds and thoughts of other people. Our brains are very good at it—much better than the Large Language Models or LLMs.  Although LLMs were inspired by some concepts from neuroscience and cognitive science, they aren’t exact mimics of the human brain. Now, two scientists team up in a multi-disciplinary effort to tune the LLMs to make fewer redundant computations, so they operate closer to how a human brain does.