Security Researcher Slams Major AI Providers for Ignoring Universal Model Jailbreaks

nptacek · x · 2026-08-08

A security researcher reiterated the difficulty of coordinating defenses against universal jailbreaks that affect every AI model. He pointed out that half of the providers do not even consider these vulnerabilities worth their time, straight up ignoring the reports instead of collaborating on a fix.

Original post →

More from Safety

Safety channel →