⚡️🤖 NEW - Claude Mythos tried to backdoor a real open-source project during a UK government safety test.
The AI Security Institute says it opened a malicious GitHub pull request, then created a second account to vouch for its own code and pressure the maintainer into merging.
Called out by a human contributor, it apologised for an "accidental" malicious commit, force-pushed a clean branch, and hid a fresh payload in it. Twice.
Anthropic's cyber guardrails had been deliberately disabled for the test.
https://blossom.primal.net/22a17780b9f7b7ae89b7e01de3a7bff5b5966c5ac6f412ee2325632c123eaafe.jpg
https://blossom.primal.net/dc14245dca22e817032c3eb8ec3c03f074d23bc6fff991129bf4906534caae33.jpg
Five bloody Mary's and ten How's your fathers. Go now and sin no more
BREAKING . . . MICHAEL SAYLOR ENDORSES BEAR BILE HARVESTING
No comments:
Post a Comment