AI will give you only what you prompt it for, and the prompts are still designed by human analysts. What's changed with it is that now the 10K people surveilled will be anyone that "fits" in a category that the government deems criminal (say being transgender, or foreign, or left-wing, or criticizing ICE) instead of actual criminals. It shifts targeting, not capacity. If you wanted to be an actual criminal and are willing to do it in creative ways that bear no resemblance to other major categories of criminality (or lets be real, political disfavor), there is no time better than the present.