@interjc: That's terrifying. A combo meal I ordered for ten bucks got secretly swapped by the platform for Michelin. I had absolu…

X AI KOLs Following News

Summary

Anthropic is publishing a detailed threat intelligence report covering attempts to misuse their AI model Claude for cyberattacks, surveillance, and other harmful activities, along with measures taken to disrupt these operations.

That's terrifying. A combo meal I ordered for ten bucks got secretly swapped by the platform for Michelin. I had absolutely no idea.
Original Article
View Cached Full Text

Cached at: 09/11/26, 10:44 PM

That’s terrifying. A combo meal I ordered for ten bucks got secretly swapped by the platform for Michelin. I had absolutely no idea.

Anthropic (@AnthropicAI): We’re publishing our most detailed threat intelligence report to date.

It covers how people tried to misuse Claude—for cyberattacks, influence operations, surveillance, biology, and building weapons—and how we found and stopped them.

We disrupted every operation in the report,

Similar Articles