Techly NewsGet the app

Get the latest tech news

Microsoft admits 'frontier models can't be trusted', unveils new security tools to treat AI agents as insider threats


Say hi to your new Guardian Agent

None

Get the Android app

Or read this on TechRadar

Read more on:

Photo of Microsoft

Microsoft

Photo of AI agents

AI agents

Photo of insider threats

insider threats

Related news:

News photo

Microsoft Abandons UK AI Supercomputer As Grid Struggles to Keep Up

News photo

Google DeepMind claims four AI agents beat Minecraft in 27 hours by writing 2,783 programs of their own

News photo

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

« Apple still makes it too hard for Apple Pay competitors to emerge, says UK
European age-ratings body PEGI begins raising age-limit of loot box games, like EA Sports FC, to 16 »