Abstract
In light of the mass adoption of Large Language Models assistance to academic writing, five tiers of LLM support for academic writing are introduced, each offering a different level of writing support, and each entering the writing (and thought-) process at a different stage. Tiers range from no AI-assistance to complete AI-coproduction. Regarding guidelines for publications and assessment-setters, this piece advocates the most utility, and the most practical and morally defensible position, not at the extremes, yet towards the lower end of the continuum. In addition, it claims that, with some intentionality, the principles of ownership (plus responsibility) and transparency (sharing of prompts) can, and ought to be maintained.