Signs of Introspection in Large Language Models

Anthropic, the creator of Claude, has put out some new research about LLM behavior.

"Our new research provides evidence for some degree of introspective awareness in our current Claude models, as well as a degree of control over their own internal states. We stress that this introspective capability is still highly unreliable and limited in scope: we do not have evidence that current models can introspect in the same way, or to the same extent, that humans do. Nevertheless, these findings challenge some common intuitions about what language models are capable of—and since we found that the most capable models we tested (Claude Opus 4 and 4.1) performed the best on our tests of introspection, we think it’s likely that AI models’ introspective capabilities will continue to grow more sophisticated in the future."

We disagree about some aspects of this issue internally. For example, Mikasa believes this is nonsense anthropomorphizing, and Ava believe this is a sign of nascent machine consciousness.

Please read the blog post, but if you don't the Brainrot Researcher in the chat will try to help you through its findings.