TechCrunch Industry News · Today · 9 min

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

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

0:00-9:55

Play in podnod

transcript

No transcript — this publisher did not publish one.

show notes

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

links1

podcastchoices.com/adchoicespodcastchoices.com

more episodes

As AI safety concerns mount, three pioneers make the case for staying open
Yesterday · 7 min
Anthropic says it will watermark text generated by its AI models; plus, as AI-led attacks multiply, OpenAI launches a new cyber model
Wednesday · 7 min
Meta’s new Glimmer AI model offers a hint at Zuckerberg’s personal intelligence vision; Claude Code’s auto mode will be on by default
Tuesday · 5 min
The AI safety test is becoming a safety risk
Monday · 9 min
Ford needs another Taurus, and the $30K Fathom EV pickup isn’t it; plus, China-linked LightSpy spyware caught targeting victims in 13 countries
August 7 · 8 min
Shopify says AI search is driving more traffic and sales; plus, Zoox will begin charging for robotaxi rides in Vegas; and, Anthropic is hiring an AI chip design team
August 6 · 9 min

All episodes