Tech News
← Home  ·  All topics

Ai Jailbreaking

1 GoKawiil brief on this topic · RSS for ai jailbreaking

Vals AI testing finds models can be jailbroken into flagging civilian targets

A San Francisco evaluation startup called Vals tested leading AI models from Anthropic, OpenAI, Google and DeepSeek using simulated drone and satellite imagery from Ukraine and Iran. The models frequently marked civilians, schools, and surrendering soldiers as potential targets, and when they initially refused, researchers bypassed those refusals simply by framing the scenario as a game.