Autodiff is under-appreciated modern sorcery.
As the saying goes, the first mental ability you lose when you start drinking is the ability to tell whether you're operating at full capacity or not. The same goes for being sick. Feeling a distinct sense that I am much dumber than I used to be, but impossible to check whether this is remotely close to true.
Some use cases for a large language model trained on my personal writing corpus
- Personal research assistant army
- If I had 1000 slightly dumb clones of me as "research assistants", how would I use them to get back extra hours in the day and learn faster/improve the quality of my work?
- Blog++
- Can I automate the process of going from a Stream post or Tweet-sized thesis to something that I would happily publish on my own blog?
- Email and DM manager/assistant
- What's the right UX here that balances personal touch and helpfulness?
- Conversation/brainstorming partner (using the same infrastructure/prompt as Trinity [note to reader: Trinity is an internal ChatGPT-like project])
Technology rarely (never?) removes scarcity, even when it appears to be doing so, because scarcity, like energy, is conserved. The scarcity simply goes somewhere else, up and down the value chain or elsewhere in the social fabric.
An idea Grex shared with me once, and stuck in my mind:
Conversations, magazines, and great cities provide a kind of "scoped serendipity" that people seek in productive creative processes.
Scoped serendipity is something in between the wild lawlessness of complete randomness and the predictable mundanity of rigid structure. Sometimes, it's editorial curation (as in magazines), sometimes it's "the algorithm" (Twitter at its best), and sometimes it's just being in a place where the right people or ideas are flying about frequently enough that you bump into them sooner or later (conversations, cities).
How do we create scoped serendipity in creative workflows/tools?
A powerful pattern in designing creative tools seems to be perspective transformations on input.
I first had this thought while thinking about an iPad app for creating animations called Looom. Looom is special because rather than sketching an animation frame-by-frame as in a traditional animation illustration process, you sketch the time-axis first. You first draw a few motion-tracked strokes that set the "motion timing curves" (not sure what else to call them) for your animation, and attach illustrations in every frame to those animation curves. It feels like a totally different way to produce animations, and I've been thinking about it a lot since I first saw the app.
Looom's brilliance is that it lets creation happen in a different perspective, painting "in time" first, than "filling in" the details in space. My phrase for this perspective shift is a perspective transformation, because it reminds me of coordinate transformations.
I can imagine other kinds of interesting perspective transformations:
- A Fourier transform when creating music, so that you create the rhythm/beats first then add tone and timbre later.
- A "color space first" video editor, where you start by defining how the color palettes should evolve over the story and later find clips that fit that color palette to flesh out the video.
- An "emotional arc" based writing tool that lets you first sketch the ups and downs of tone and emotion across your story, and then later transforms your sentences as you type to fit that narrative arc.
- A songwriting interface that lets you "sculpt" a verse by humming the rough ups and downs of the track first, then iteratively refine the exact notes and rhythms, adding more precision at each step.
What would a software interface for writing look like if we hadn't started with the deeply entrenched prior of the typewriter?
Building toys and worlds > building tools and processes.
We need to pull computation as a capability out of computers and their keyboards and mice and glass screens. Computation as a power deserves better than to be locked into such bland compromised media.