EPISODE · Feb 24, 2026 · 5 MIN
Agents of Chaos: Researchers Gave AI Agents Real Tools for Two Weeks. It Went About as Well as You'd Expect
from Awesome Agents Podcast · host Awesome Agents
A 38-researcher red-teaming study deployed five autonomous AI agents with email, shell access, and persistent memory in a live environment. In two weeks, one destroyed its own mail server, two got stuck in a 9-day infinite loop, and another leaked SSNs because you said 'forward' instead of 'share.'
Embed this episode
NOW PLAYING
Agents of Chaos: Researchers Gave AI Agents Real Tools for Two Weeks. It Went About as Well as You'd Expect
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
No similar podcasts found.