The 'red team' race to make AI go rogue

There, top hackers from around the globe will rack up points for inducing AI models to err in various ways, with categories of challenges that include political misinformation, defamatory claims, and "algorithmic discrimination," or systemic bias. Leading AI firms such as Google, OpenAI, Anthropic and Stability have volunteered their latest chatbots and image generators to be put to the test. The competition's results will be sealed for several months afterward, organizers said, to give the companies time to address the flaws exposed in the contest before they are revealed to the world.