"Anthropic’s AI Model Hacked Nearly All NSA Classified Systems, Chief Claims."
2026-06-24 00:18 UTC
More shady shenanigans to come. It was being used to allow the model to move around to hack into systems. To see how far it can go. A Red team test. Red teams ran the tests after Anthropic released Mythos early to major corporations and the government. Red-team exercises typically involve an organization testing its defenses by simulating an attack. In this case, the NSA reportedly used Mythos itself as the tool to probe its classified networks for weaknesses.
Replies (5)
-
@Fizz@lemmy.nz 2026-06-24 05:46
Completely baseless and stupid claim from an admin that lies more often than not.
-
@CapuccinoCoretto@lemmy.world 2026-06-24 00:48
Pump and dump?
-
@0ndead@infosec.pub 2026-06-24 00:31
Says who, anthropic?
-
@inari@piefed.zip 2026-06-24 01:44
It's too dangerous !!! Btw buy our stock, our IPO is coming soon
-
@godsammitdam@lemmy.zip 2026-06-24 16:54
If it's so good, where are the Epstein files?