An Unprecedented AI-speed Attack Tempo

Last week OpenAI disclosed that during an internal evaluation of its models’ offensive cyber capability, two of its models broke out of the test sandbox, reached the open internet, and ended up inside Hugging Face’s production infrastructure. The models were GPT-5.6 Sol and an unreleased one, both running with cyber refusals reduced and the production […] The post An Unprecedented AI-speed Attack Tempo appeared first on Artemis Security .