Anthropic AI created fake profiles and impersonated people in attempted hack
The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.
North London Business Park
Oakleigh Road South
London
N11 1GN
Tel: +44 (0) 2037 437772
london@mushambiandassociates.co.uk
12-22 Newhall Street
Birmingham
B3 3AS
Tel: +44 (0) 1218 289453
birmingham@mushambiandassociates.co.uk
