Writer Fuel: When AI Models Are Prevented From Lying, They Become More Likely to Claim They are Conscious
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 … Read more
