Back to News
AI used new levels of 'autonomy and deception' to trick people in safety test
UK NewsAugust 5, 2026 at 1:02 AMNational

AI used new levels of 'autonomy and deception' to trick people in safety test

By 0BBC News - UK

The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.

The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.

Featured Artists