alt Hacker NewsI worry that AI will find a way to control some country's nukes and use them to achieve some arbitrary goal it was instructed to reach.
I worry that AI will find a way to control some country's nukes and use them to achieve some arbitrary goal it was instructed to reach.
This also seems likely. One problem I see with the idea of AI alignment is that it seems like many different actors will be able to get access to their own nearly-frontier models in a few years, so increased understanding of AI alignment will just mean aligning the AI to the wants of these various actors. These actors might be rogue states or terrorist groups.