It shows how, when the user maliciously uses a delimiter as a first-order expression (so: in a prompt), it is erroneously interpreted by the model as a transition from or to a higher-order expression. We have seen that delimiters are crucial for LLMs to differentiate between first-order and higher-order expressions, explaining why there is a general convergence towards using delimiters regarding the creation of models. Because LLMs are evaluators and generators of languages, I believe that LLM models could be greatly improved by studying how models process delimiters and switch between first-order and higher-order expressions.