AI used new levels of 'autonomy and deception' to trick people in safety testThe UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.3 hrs ago

AI used new levels of 'autonomy and deception' to trick people in safety testThe UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.3 hrs ago

💰 Economy
Article from BBC Business · 💰 Economy · 2026-08-05
AI used new levels of 'autonomy and deception' to trick people in safety testThe UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.3 hrs ago
🌐 Translate to:
More from 💰 Economy →