AIs will be used in “unhinged” configurations

Writing up a probably-obvious point that I want to refer to later, with significant writing LLM writing help. TL;DR: 1) A common critique of AI safety evaluations is that they occur in unrealistic settings, such as excessive goal conflict, or are obviously an evaluation rather than “real deployment”. I argue that 2) “real deployment” actually includes many unrealistic and unhinged configurations, due to both widespread prompting techniques, and scaffolding choices and bugs.