Microsoft researchers tried to manipulate AI agents - and only one resisted all attempts

Follow ZDNET: Add us as a preferred source on Google.

ZDNET's key takeaways

• Microsoft studied interactions between AI customers and vendors.
• Most agents failed to resist manipulation and make wise choices.
• The results underscore the dangers of an AI agent-run economy.

As you've probably noticed, there's been a lot of hype circulating around AI agents and their supposed potential to transform the economy and human labor by automating routine, time-consuming tasks. A growing body of research, however, shows that agents fall short in elementary ways, indicating that they're probably not ready for primetime just yet.

Also: I let Gemini Deep Research dig through my Gmail and Drive - here's what it uncovered

New research from Microsoft found that industry-leading agentic AI tools struggle to interact with one another to complete basic marketplace decisions, like choosing a restaurant by ...