New Delhi, Aug. 28 -- IN A RECENT experiment on Claude Sonnet 4.5, a large language model (LLM) from Anthropic, researchers asked it to count to five and, at the same time, "introspect deeply". The artificial-intelligence model complied, returning: "One . Two . Three . Four . Five ." So far, so normal.

During the task, the researchers were watching what was going on inside the LLM's many layers of artificial neural networks. When a user asks a question, the words are turned into chunks of text (tokens) that are then converted to numbers. These are then passed through the layers of artificial neurons until they reach the final layer, which produces a token. Repeat that process a bunch of times each second and you get a series of tokens th...