Reuters:

Anthropic says it found 5,500 verified vulnerabilities in April-October and Glasswing partners found 129K+ in April-July; 33K+ were critical or high severity  —  Anthropic is expanding a program that allows vetted cybersecurity professionals to test its most powerful AI models with fewer safeguards …

Reuters:

Anthropic says it found 5,500 verified vulnerabilities in April-October and Glasswing partners found 129K+ in April-July; 33K+ were critical or high severity  —  Anthropic is expanding a program that allows vetted cybersecurity professionals to test its most powerful AI models with fewer safeguards …

Source: TechMeme
Source Link: https://www.techmeme.com/261006/p36#a261006p36