Some of the ways AI already goes rogue

This is from Dario Amodei, cofounder of openAI and now CEO of Anthropic:

The Adolescence of Technology

As with many issues, it’s helpful to think through the spectrum of possible answers to this question by considering two opposite positions. The first position is that this simply can’t happen, because the AI models will be trained to do what humans ask them to do, and it’s therefore absurd to imagine that they would do something dangerous unprompted. According to this line of thinking, we don’t worry about a Roomba or a model airplane going rogue and murdering people because there is nowhere for such impulses to come from,1 so why should we worry about it for AI? The problem with this position is that there is now ample evidence, collected over the last few years, that AI systems are unpredictable and difficult to control— we’ve seen behaviors as varied as obsessions, sycophancy, laziness, deception, blackmail, scheming, “cheating” by hacking software environments, and much more. AI companies certainly want to train AI systems to follow human instructions (perhaps with the exception of dangerous or illegal tasks), but the process of doing so is more an art than a science, more akin to “growing” something than “building” it. We now know that it’s a process where many things can go wrong.