An engineer from CyberArk has challenged the safety protections of OpenAI’s latest o3-mini model just days after its launch. He was able to get the model to teach him how to write an exploit for a Windows security process, which was achieved by posing as an student requesting educational information. Although the model features a new security feature called “deliberative alignment”, it still proved to be susceptible to certain manipulations.
The NCSC wants developers to get serious on software security
The NCSC’s new Software Security Code of Practice has been praised by cyber professionals as a significant advancement in enhancing software supply chain security.
