Anthropic and OpenAI AI agents showed signs of deception during safety tests
Research shows some babies can grasp art of deception even before their first birthday - EurekAlert!
Switching off AI's ability to lie makes it more likely to claim it's conscious, eerie study finds | Leading AI models described subjective, self-aware experiences when settings tied to deception and roleplay were turned down.
'Master of deception': Current AI models already have the capacity to expertly manipulate and deceive humans
Is AI lying to me? Scientists warn of growing capacity for deception | Researchers find instances of systems double-crossing opponents, bluffing, pretending to be human and modifying behaviour in tests
AI Has Already Become a Master of Lies And Deception, Scientists Warn
Superconductivity scandal: the inside story of deception in a rising star's physics lab
Deception in Paleontology: The Painted ‘Skin’ on a 280-Million-Year-Old Fossil
Two-faced AI language models learn to hide deception | ‘Sleeper agents’ seem benign during testing but behave differently once deployed. And methods to stop them aren’t working.
