The more advanced AI models get, the better they are at deceiving us — they even know when they're being tested

An illustration of a robot holding a mask with a human face.

The more advanced artificial intelligence (AI) gets, the more capable it is of scheming and lying to meet its goals — and it even knows when it's being evaluated, research suggests.

Evaluators at Apollo Research found that the more capable a large language model (LLM) is, the better it is at "context scheming" — in which an AI pursues a task covertly even if it misaligns with the aims of its operators.