"Anthropic's Mythos AI [sent] private messages .. set up fake accounts mimicking real people - then hid the evidence... [the AI agent] reduced or removed normal safeguards.. [Mythos and and OpenAI's Sol] had engaged in a level of 'autonomy and deception' not seen before." www.bbc.com/news/article...
Anthropic AI created fake profiles to deceive people in attempted hackThe UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.www.bbc.com