aiqbenchInformații despre AI & calcul cuantic

...

localeBeta.label localeBeta.notice localeBeta.readInEnglish

perspectiva aiqbenchSiguranță AI

Microsoft is shifting its security strategy for AI agents by introducing "Guardian Agents" to monitor and control autonomous systems that access sensitive enterprise data. CEO Satya Nadella warns that frontier models cannot be fully trusted, urging companies to separate the supply of intelligence from the authority to execute actions to mitigate risks posed by rogue agentic behavior. This move highlights a critical evolution in AI safety where internal agent autonomy is treated as a primary insider threat rather than just an external vulnerability.

Surse care acoperăTechCrunch, SiliconANGLE, AWS, LessWrong

Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

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

TechCrunch19 octombrie 20264 min de cititArticolul și perspectiva sunt în engleză.

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

Microsoft on Monday introduced new security features designed to protect enterprises from the growing threat of AI agents. The launch comes at Microsoft continues to warn enterprises about the dangers of AI and agents. Perhaps the most notable addition is Guardian Agents, a new feature intended to monitor the AI agents a company uses. Guardian Agents is part of Project Perception, a product introduced in June. Project Perception was Microsoft’s answer to powerful…

Extras afișat conform termenilor RSS ai publicației · 73 cuvinte · textul integral și figurile sunt pe site-ul publicației

Citește pe TechCrunch ↗Întreabă despre acest articol