I think there’s arguments to be made both ways. I‘m generally of the belief that technology that works is a net win for humanity. But I think we need to stop being vague about what it means for an LLM to work. For me, I just want to tell an LLM to replace all the hard coded strings in my app with translation tags. Sadly, this isn’t possible to do reliably with what we have today. I’m not sure who’s job this would eliminate other than my own. I think the more existential questions are about if we made a god box that could perform all the white collar jobs. I think we’re so far away from that despite being sold that vision, that we might as well consider the moral and philosophical implications of a time machine or teleportation device if we’re going to continue to entertain AI doomerism for LLMs.