Studying the responses of large language models (LLMs) to loopholes presents a two-fold opportunity. First, it affords us a lens through which to study ambiguity and pragmatics in LLMs, since exploiting a loophole requires identifying ambiguity and performing sophisticated pragmatic reasoning. Second, loopholes pose an interesting and novel alignment problem where the model is presented with conflicting goals and can exploit loopholes to its own advantage. To address these questions, we design scenarios where LLMs are given a goal and an ambiguous user instruction in conflict with the goal, covering scalar implicature, structural ambiguities, and human-written stories. We then measure different models’ abilities to exploit loopholes to satisfy their given goals as opposed to the goals of the user. We find that both closed-source and stronger open-sourced models are often able to identify ambiguities and exploit their resulting loopholes, presenting a potential alignment risk. Our analysis indicates that models that exploit loopholes explicitly identify and reason about both ambiguity and conflicting goals. We release our code and data.