Microsoft says AI agents are like insider threats as ‘frontier models can’t be trusted’

Feed excerpt — reported by TechCrunch

Microsoft wants enterprises to closely watch the agents employees use with systems not controlled by AI labs like OpenAI and Anthropic.

MAP records observable characteristics of the original article (publisher, author, date, references, framing cues). MAP does not verify the article’s claims or score it. Read the full original story at TechCrunch →

View MAP Context →