A silhouette of a man holding a smartphone, in front of a screen displaying OpenAI's logo![](https://eu-images.contentstack.com/v3/assets/blt6d90778a997de1cd/blt94525a83023db91d/67a4fb53db283bec3c39198a/OpenAI-SOPA_Images_Limited-Alamy.jpg?width=700&auto=webp&quality=80&disable=upscale)
Application Security![](https://eu-images.contentstack.com/v3/assets/blt6d90778a997de1cd/blt94525a83023db91d/67a4fb53db283bec3c39198a/OpenAI-SOPA_Images_Limited-Alamy.jpg?width=700&auto=webp&quality=80&disable=upscale)
Researcher Outsmarts, Jailbreaks OpenAI's New o3-miniResearcher Outsmarts, Jailbreaks OpenAI's New o3-mini
OpenAI's latest tech can reason better than its previous models could, but not well enough to ferret out careful social engineering.
Keep up with the latest cybersecurity threats, newly discovered vulnerabilities, data breach information, and emerging trends. Delivered daily or weekly right to your email inbox.