Image: storage.ghost.io · rights & removal
Watching Agents Work: A Behavioral Audit of Offensive
Reporting by ProjectDiscovery BlogRead the original at projectdiscovery.io
Security LLM Runs What closed and open models actually do when you tell them to hack a website Summary The cybersecurity capability of a model is currently measured by a solve rate, a percentage, and that number tells you almost nothing worth knowing. It doesn't tell you how the model behaved.