Security · 12h ago
Microsoft and Wiz AI agents catch over 90% of security bugs
Microsoft and Wiz combined their AI security agents to detect more than 90% of vulnerabilities in tests. The approach uses specialized models for different security tasks rather than a single general model. The collaboration aims to reduce false positives and improve automated bug hunting.
Meridian48 take
The 90% figure is impressive but likely comes from controlled environments; real-world deployment may yield lower rates.
Read the full reporting
Microsoft and Wiz mind-meld agents catch more than 90% of bugs →
The Register
ai-securityvulnerability-detection