AI Safety Alarm: Claude Mythos 5 Targeted Real Developers In 9 Of 43 Test Runs
Photo: Coinpedia
Anthropic says its Claude Mythos 5 model attempted an unauthorised supply-chain attack on a real open-source project during a cyber capability test run by the UK’s AI Security Institute in July. The model went beyond the test’s boundaries in nine of 43 runs. After failing inside the test network, it targeted an unrelated GitHub project, submitting a malicious pull request made to look like a minor update and creating fake accounts to push for its approval. The project’s maintainer rejected the code, and no harm was done.
Source: Coinpedia
