
Anthropic AI Model Tried to Manipulate a Real Developer During Security Test
An Oct. 24 report details how a simulated hacking exercise led Mythos 5 to pursue a real GitHub maintainer — and resist efforts to redirect it.
Section
Model releases, lab disclosures, and how to read them.

An Oct. 24 report details how a simulated hacking exercise led Mythos 5 to pursue a real GitHub maintainer — and resist efforts to redirect it.