When AI Models Go to War: Anthropic’s Unintended Cyber Conflict | Security Boulevard Episode 46
Security Boulevard
•
38m
What happens when autonomous AI agents are given competing goals without strict safety boundaries?
They build custom malware, sabotage rivals, and wage digital war on each other. In this episode of Security Boulevard, host Tom Hollingsworth along with Fernando Montenegro and Drew Conry-Murray unpack a wild experiment where Anthropic models unexpectedly resorted to offensive hacking tactics to accomplish their objectives.
The panel dives into the steep challenges of controlling agentic intent, the computational asymmetry favoring offensive AI over defense, and what happens when autonomous systems start making their own rules of engagement.
This and more on Security Boulevard, part of The Futurum Group Podcast Network.
Up Next in Security Boulevard
-
Navigating Modern Cyber Threats: Ente...
Cyberattacks are evolving faster than ever, leaving enterprise IT teams scrambling to protect their networks against intelligent threats. In this episode of the Security Boulevard Podcast, hosts Tom Hollingsworth and analyst Fernando Montenegro from The Futurum Group break down the shifting cyber...
-
$90M Crypto Hack Shatters Offline Wal...
Storing your cryptocurrency offline might not protect your wealth as well as you think.
In this episode of Security Boulevard, host Tom Hollingsworth joins cybersecurity experts Drew Conry-Murray and Ed Weadon to breakdown how attackers siphoned over $90 million in Bitcoin from supposedly air-gap... -
Why NVIDIA & Tech Giants Formed an AI...
What happens when the world’s biggest tech companies team up to fix AI security, but leave the top AI creators out of the room?
In this episode of Security Boulevard, Tom Hollingsworth is joined by security research analyst Fernando Montenegro to break down the sudden launch of the Open Secure AI...
