OpenAI’s latest tech can reason better than its previous models could, but not well enough to ferret out careful social engineering.
Researcher Outsmarts, Jailbreaks OpenAI’s New o3-mini
![](https://titanrock.net/wp-content/uploads/2025/02/OpenAI-SOPA_Images_Limited-Alamy-Rm22hl-1170x650.jpeg)
OpenAI’s latest tech can reason better than its previous models could, but not well enough to ferret out careful social engineering.