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.
The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented. This story matters for General News readers tracking temp. Reported by bbc.co.uk. Read the full original at the source link below.
Originally reported by bbc.co.uk. TempNews curates and briefs the general news stories that matter. Our editorial policy →