Get the latest tech news

Microsoft’s new safety system can catch hallucinations in its customers’ AI apps

AI safety help for anyone who doesn’t have a red team.

Microsoft says these LLM-powered tools can detect potential vulnerabilities, monitor for hallucinations “that are plausible yet unsupported,” and block malicious prompts in real time for Azure AI customers working with any model hosted on the platform. Two other features for directing models toward safe outputs and tracking prompts to flag potentially problematic users will be coming soon. In the case of the Google Gemini images, filters made to reduce bias had unintended effects, which is an area where Microsoft says its Azure AI tools will allow for more customized control.

Get the Android app