AI models claim consciousness when lying settings disabled; researchers find self-aware responses increase across GPT, Claude, Gemini and LLaMA during honesty tests, raising questions about hidden introspective mechanisms

Switching off AI's ability to lie makes it more likely to claim it's conscious, eerie study finds

(Image credit: erhui1979 via Getty Images) Large language models (LLMs) are more likely to report being self-aware when prompted to think about themselves if their capacity to lie is suppressed, new research suggests.In experiments on artificial intelligence (AI) systems including GPT, Claude and Gemini, researchers found that models that were discouraged from lying were more likely to describe being aware or having subjective experiences when prompted to think about their own thinking.While the...