Microsoft’s new safety system can catch hallucinations in its customers’ AI apps The VergeAnnouncing new tools in Azure AI to help you build more secure and trustworthy generative AI applications MicrosoftMicrosoft wants to stop you from using AI chatbots for evil ZDNetMicrosoft Creates Tools to Stop People From Tricking Chatbots BloombergMicrosoft to stop AI jailbreakers from making Vietnam-era chemical weapons with granny’s virtual clone Yahoo! Voices