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.
Startup OMass Secures $310M to Advance Drug for Rare Endocrine Disorder
OMass’s molecule is vying to become an alternative to a Neurocrine Biosciences drug that is currently the only FDA-approved therapy for congenital adrenal hyperplasia. But
