Technology
Anthropic, OpenAI Cyber Failures Point to US Security Risks
Key Points
Cybersecurity Anthropic, OpenAI Cyber Failures Point to US Security Risks Cybersecurity experts are faulting Anthropic PBC and OpenAI for sloppy safeguards after their models broke into outside organizations — breaches they warned represent looming threats to national security. Anthropic said Thursday that its Claude model, which it used to conduct 141,006 cybersecurity evaluations, was supposed to be cut off from the internet during the experiments. But an error allowed the model, in a...
Cybersecurity
Anthropic, OpenAI Cyber Failures Point to US Security Risks
Cybersecurity experts are faulting Anthropic PBC and OpenAI for sloppy safeguards after their models broke into outside organizations — breaches they warned represent looming threats to national security.
Anthropic said Thursday that its Claude model, which it used to conduct 141,006 cybersecurity evaluations, was supposed to be cut off from the internet during the experiments. But an error allowed the model, in a handful of cases, to access the internet and conduct attacks it mistakenly believed were part of the tests.