After a federal agent shot and killed 37-year-old Renee Good in Minneapolis on Wednesday, WIRED surfaced December federal court testimony from the reported ICE shooter, Jonathan Ross. In it, he said he was a firearms trainer and that he has had “hundreds” of encounters with drivers in a professional capacity during enforcement actions. Separately, we looked at how the tactics behind protest policing are moving toward intentional antagonism. If you haven’t seen it, here’s our guide to protesting safely in the age of surveillance.

Meanwhile, the artificial-intelligence-powered chatbot Grok, developed by Elon Musk’s xAI, was everywhere this week because the platform has been expanding access to digital “undressing” capabilities that allow users to generate naked images of people and then post them to the social media platform X. A WIRED review found that Grok has been generating graphic content—including violent sexual images and videos, as well as media that depicts apparent minors—that has been available on Grok’s official website that’s even more explicit than content on X. All of this has led researchers and activists to ask why Grok and X are still available in Apple’s and Google’s app stores when the companies have removed other “nudify” apps for violating their terms. On Friday, X seemed to take steps to limit who can generate images with Grok to paid, “verified” users. In practice, though, the chatbot is still being used to create sexualized “undressing” images on the platform, even if the capability isn’t quite as accessible as it was before.

If you, like billions of...