Groundbreaking Study Uncovers 139 Ways AI Models Can Misbehave, Raising Concerns

In a groundbreaking study, US researchers uncover 139 novel ways AI models can misbehave, including generating misinformation and leaking personal data, raising concerns about AI safety and highlighting shortcomings in a new government standard for testing AI systems.

• The US government conducted a study on frontier AI models to test their safety and identify potential vulnerabilities.
• Researchers found 139 novel ways to make the AI systems misbehave, including generating misinformation or leaking personal data.
• The study also revealed shortcomings in a new US government standard designed to help companies test AI systems.