AI security Archives | CyberScoop

AI security

OpenAI and Anthropic said they turned over their models to government researchers, who found an array of previously undiscovered vulnerabilities and attack techniques. (Image via Getty)

Anthropic touts safety, security improvements in Claude Sonnet 4.5

Even with all the testing, the company said in its released research that the model tightened up once it was “aware” it was being evaluated.

2 hours ago By Derek B. Johnson