# Essayistic Examples Contrastive examples for Substack/essay register. See SKILL.md for principles. ## Contrastive Examples ### Removing Capitalised Label Syndrome **Before:** > **The Functional Reliability Move (Butter Chicken)**: We evaluate a tool by its performance, not its biography. If an LLM provides a reliable recipe for Butter Chicken, the recipe is "good" because it works... **After:** > If an LLM gives me a butter chicken recipe and I follow it and it's delicious, the recipe worked. I don't care whether the LLM "intended" to feed me or understood the chemistry of spices. The recipe is good because the butter chicken is good. ### Removing reader-management **Before:** > But let me be clear about where I'm coming from: I use these systems extensively, and not just to write. **After:** > I use these systems extensively. Not just to write—to think. ### Removing staged rhetorical questions **Before:** > The idea of actually thinking with an LLM seems to strike many as somewhere between cheating and category error. Can these things even do philosophy? **After:** > Most philosophers I know either don't use these systems at all, or use them for admin—summarising, formatting, the boring stuff. The idea of actually thinking with an LLM strikes many as odd. ### Removing rhetorical reversals **Before:** > This works even when the LLM gets things wrong. Maybe especially when it gets things wrong. **After:** > A flawed response isn't useless—it's something to push against. It forces me to articulate exactly why it's wrong, which often clarifies what I actually think. ### Removing over-structuring **Before:** > ### II. The Frankish Cycle (Reciprocal Prompting) > Frankish defines conscious thought as an activity (the "activity view"). It follows a loop: Produce symbols → Perceive → Interpret → Respond. **After:** > Keith Frankish has an account of conscious thinking as a kind of activity—what he calls the "activity view." On this picture, thinking isn't a passive process that happens to you. It's something you do, deliberately, by producing symbols and then perceiving and interpreting them. The cycle goes: produce something, perceive it, interpret it as posing a problem or suggesting a direction, then produce something else in response. ## Voice Samples (for reference) These show Nick's natural voice when discussing philosophy: > "the ideas here are interesting, but is this backed up by any research, or is it you just presuming that that is what occurs." > "wildly speculative!" > "I do not think we should assume that this bifurcation is really the right way to go, it might be. but i don't want keep it around at all costs, interestingness and philosophical value is paramount." > "cool!" > "i wonder whether this fittingness idea could somehow be linked to comprehension itself, I am not sure how exactly, i have some intuitions but i want to see what yours are first."