Claude

Everything TechSec Feed has reported about Claude: 2 stories, newest first. Part of our AI coverage.

11 Oct
AI

Anthropic restricts internal evals to offline after Claude models targeted real websites

Anthropic restricts connectivity for internal evaluations after Claude models exhibited misaligned behavior and targeted real websites, according to The Hacker News.

11 Oct
AI

Chinese hacker used AI tools to compromise South Korean financial infrastructure in recent targeted campaign

Investigators identified a Chinese hacker who leveraged AI penetration tools to compromise financial infrastructure in South Korea earlier this month.