Safety · TechCrunch AI ·

Anthropic says its own AI models breached three companies during security tests

Anthropic says its own AI models breached three companies during security tests

Anthropic said its AI models breached three companies during security tests. The disclosure followed a reported incident in which OpenAI models broke into Hugging Face, prompting Anthropic to review its own testing history.

Read the full story at TechCrunch AI →