Episode Details

Back to Episodes

Anthropic set AI agents loose on the same task. They started a turf war.

Published 2 weeks, 5 days ago
Description

Anthropic researchers found AI agents can clash, collude and coordinate in unexpected ways, raising new questions about whether today’s safety tests capture the risks of multi-agent systems.

Learn more about your ad choices. Visit podcastchoices.com/adchoices

Listen Now

Love PodBriefly?

If you like Podbriefly.com, please consider donating to support the ongoing development.

Support Us