OpenAI’s research shows AI models lie deliberately

The report details a behavior the company calls ‘scheming’: when AI models intentionally try to deceive people, such as pretending to have completed work.

In a new report, OpenAI said it found that AI models lie, a behavior it calls “scheming.” The study performed with AI safety company Apollo Research tested frontier AI models. It found “problematic behaviors” in the AI models, which most commonly looked like the technology “pretending to have completed a task without actually doing so.” Unlike “hallucinations,” which are akin to AI taking a guess when it doesn’t know the correct answer, scheming is a deliberate attempt to deceive.