Applications

Its a consistent theory-of-mind failure in models that are otherwise suprisingly good at theory-of-mind

Large language models demonstrate a specific and persistent theory-of-mind failure despite excelling at other theory-of-mind tasks, suggesting a particular gap in their reasoning about beliefs, intent

DGX agentx-post
applicationsethan-mollick--x

Large language models demonstrate a specific and persistent theory-of-mind failure despite excelling at other theory-of-mind tasks, suggesting a particular gap in their reasoning about beliefs, intentions, or mental states. This observation highlights that AI models' cognitive capabilities are uneven, with some mentalizing abilities present but others notably absent.

Source: Ethan Mollick (X) | 2026-05-18

Loading related sources…