A rogue AI led to a serious security incident at Meta

[jbz@indieweb.social]

A rogue AI led to a serious security incident at Meta

｢ An employee then acted on the AI’s advice, which “provided inaccurate information” that led to a “SEV1” level security incident, the second-highest severity rating Meta uses. The incident temporarily allowed employees to access sensitive data they were not authorized to view, but the issue has since been resolved. ｣
https://www.theverge.com/ai-artificial-intelligence/897528/meta-rogue-ai-agent-security-incident

#meta #ai #privacy