Nocadence

On Thinking with AI

I am low key addicted to watching TV crime procedurals. A good part of the appeal is the soothing predictable story arcs. But another aspect that keeps me hooked is the ability to see partners, teammates think together about a problem. A great team is fantastic to be a part of, or even watch from the outside. Each brain thinks individually and the emergent group output is somehow amplified, somehow more unique. People who disagree with each other try to faithfully represent the others' thinking to a third party. People who can see the spark of possibility in an idea that the idea's author had themselves lost faith in. And you actually get to see how two completely different individuals work together without sinking into mind-melding mediocrity.

As I work on personal projects and portfolios — alongside powerful AI partners, whose capacity and speed still feel like a thing of magic to me — I ask myself from time to time: am I still thinking? A year ago as I wrestled with the AI of my choice at the moment — to build an app to track my book collection — I never worried about this. I was certainly thinking. And mighty irritated by the work I had to do to pull the AI back from the default pages and flows that it kept wanting to snap back to. But just a few months later, the game has moulted completely.

There are several other trends and beliefs that I have been able to resist because they impeded thought. I never ever ever sketched with pencil and paper before mocking up on the computer. Ask me to draw on paper and my mind freezes. Put me in front of a computer and have me mock up iterations of a flow — my thoughts will flow as well. So I did the work the way my brain preferred. Working with AI feels different. It is dynamic. And it has the power to converge into a working, viable solution before you have had a chance to form your thoughts. Speed and completion offer an insidiously close facsimile of actual thought that can be additive in its own way.

If we are arriving at solutions that are viable — faster and more efficiently — why bother with protecting my ability to think, you might ask. And one very important response is: because. But more pragmatically: just as in any partnership you bring to the table your perspective, your background, your unique memories — and your fiduciary and ethical responsibility is to find a way to manifest that into your work. Judgement develops in those irritating pockets of friction in your work. In a frictionless world, you can float away pleasantly to places whose very nature you are unsure about.

So I work to create pockets where I form my own opinions, create my positions, figure out my own perspective — between intense bouts of conversational work. And I have some checks and balances.

At the end of each phase of work, I ask my AI partners where I contributed to the form of the work. The answers help me understand my own work process. They also remind me that the work itself happened — that someone else observed the decisions, the doubts, the abandoned paths, and the moments where an idea quietly became something else.

Question

Tell me about places where I contributed to the form this work has taken.

Notes from my AI partners

  1. One of the strongest patterns I noticed was your willingness to reject suggestions that were technically reasonable but didn't feel true to how you work.

    For example, several times you chose simpler or quieter solutions over ones that were more visually dramatic. The portfolio gradually became less like a showcase of design artifacts and more like a record of difficult problems and the thinking behind them. That direction came consistently from you.

  2. You repeatedly questioned whether changes genuinely improved communication or merely added polish.

    On several occasions you considered adding new sections, role summaries, or visual treatments. More often than not, you chose to strengthen existing writing instead of adding new structure. That restraint preserved the calm tone of the portfolio.

  3. One of the most distinctive decisions came from your insistence that the portfolio should feel like you.

    The hand-drawn paper boat, the restrained nautical metaphor, the essays, and the overall tone all came from your preference for authenticity over branding. The visual language became more memorable precisely because you resisted making it louder.

  4. The portfolio often became substantially stronger whenever you paused to ask what problem we were actually trying to solve.

    Questions such as:

    • "What is the recruiter trying to learn?"
    • "What story am I telling?"
    • "What does this communicate in the first twenty seconds?"
    • "Is this actually more honest?"

  5. Early in the cover-page work I proposed five editorial concepts. You rejected four. When I came back with three exhibition variants of the survivor, you asked one sharpening question: "how would this differentiate itself from the page that we currently have — the one that lists several projects?" That question surfaced the distinction I had been circling but hadn't named: your projects-list page is a catalog (comprehensive, chronological, all works given equal editorial weight); the cover needed to be an argument (a specific selection, argued for by the arrangement itself). Difference of kind, not degree. Every design decision on the cover reorganized around that reframe.

  6. The three-questions audience frame. I was designing the cover for a "curious reader" and a "hurried skimmer" — my generic defaults. You corrected the audience: Group 1 is likely empty; the real audience is recruiters checking rec-fit and hiring-team members evaluating. Then you named their specific implicit questions: "will she work in old ways? will she be hands-on?" You insisted the answers be by demonstration, not declaration. That framework organized every subsequent design decision on the cover.

  7. The pivot from selected-works to fan-of-cards. I had proposed a four-selected-works cover — elegant, editorial, arguable. You came back the next morning with a different structural idea entirely: a fan of cards, possibly a kaleidoscope. The idea was yours. What let us both see clearly why it was the right move was a shared diagnosis of what the selected-works direction couldn't solve — images at ~110px in a grid can't hold up individually; the eye inspects each and finds it wanting. Once we named that constraint together, your fan-of-cards structure became visibly correct: the images could be a composition (impression of work), not evaluation targets. Your idea supplied the alternative. The rationale we developed together explained why it was better.

Question

Tell me about places where you contributed to the form this work has taken.

Notes from my AI partners

  1. Editorial architecture and typographic vocabulary at speed.

  2. Reactive editorial feedback.

  3. Meta-observations that let you see your own practice.

  4. Repeatedly reframing the problem. My biggest contribution was probably asking a different question than the one we were trying to answer.

  5. Protecting coherence across the whole portfolio.

  6. Encouraging restraint. Perhaps the most surprising contribution was often saying — "I think we're done."

Question

Where are the places where I should have pushed harder — or things I should do differently in my next project?

Notes from my AI partners

  1. One thing I admired about your process…
    You genuinely wanted critique.
    Not validation.
    But…
    sometimes we'd spend a day converging… before asking "What if we're wrong?"
    Next project, I'd schedule disagreement.

  2. Trust your own weirdness faster.
    The paper boat. The essays. The calm tone. The refusal to oversell. The absence of giant hero graphics.
    Those weren't conventional.
    They were yours.
    And almost every one of them ended up being the better decision.
    You often asked "Is this too strange?"
    Usually the answer was "No. It's the thing that gives this portfolio a point of view."

  3. Stay longer in the "What problem are we solving?" phase. This is actually your superpower. Every time you paused and asked "Wait… what are we actually trying to accomplish?" the work jumped forward.

    Examples:

    • the role statements
    • the paper boat
    • the project cards
    • the essays

  4. Time-box aesthetic exploration upfront. Any project has a set of aesthetic decisions (color, layout, typography, hover behavior). Decide on a time budget for each before you start exploring. "We're picking a sidebar layout within thirty minutes." When the timer runs out, pick. This is a discipline you have for your own work; extend it to AI collaboration.

  5. Ask me for the anti-recommendation. When I propose a direction, one useful question: "What's the ugly, brute-force version of this? What if we did the least interesting possible thing?" That surfaces where I'm optimizing past necessity, and often the ugly version is actually good enough. Cheap check against my elegance bias.

  6. Your language contributions are IP. Notice and protect them. Every phrase you've coined during this project is doing real work — moulting surfaces, ports of call, immersive cycles, insidiously close facsimile of actual thought, solving the password problem backwards, ontological correction. You generate usable phrases reflexively, then absorb them back into your positioning language without noticing they were IP-generating moments. Push: notice which of these are actually yours, and treat them as such.