Geoffrey Litt

New longform @inkandswitch.com essay! 📜 Malleable Software: Restoring user agency in a world of locked-down apps by me, @joshuahhh.com, @pvh.ca and @seaofclouds.com inkandswitch.com/essay/mallea... It's about why people need agency over their software tools, and how to make that happen.

what if you could model a problem in a spreadsheet, and then instantly start applying powerful *filters* to explore your space of options? that's the idea @alexwarth.bsky.social and I have been exploring recently at @inkandswitch.com ... 1/

you can also write any spreadsheet formula you want and use the result as a filter 😎 and, you can filter on *outputs* and filter "backwards" showing what inputs are compatible w/ that output! eg: in this video we see what we can afford while staying under budget: 5/

what if you could model a problem in a spreadsheet, and then instantly start applying powerful *filters* to explore your space of options? that's the idea @alexwarth.bsky.social and I have been exploring recently at @inkandswitch.com ... 1/

one way to explore a space is *filters*. we've all seen filters on shopping websites: you can use checkboxes, range sliders, etc to narrow down a list. we can borrow from that familiar paradigm and bring it into our ambsheet. 3/

what if you could model a problem in a spreadsheet, and then instantly start applying powerful *filters* to explore your space of options? that's the idea @alexwarth.bsky.social and I have been exploring recently at @inkandswitch.com ... 1/

Personal news: I’m a dad now! My wife and I are feeling very fortunate 😊

One of my all-time favorite talks: how to write so people will care what you have to say. First watched it many years ago and I still think about it constantly. youtu.be/aFwVf5a3pZM

“In the real world - not in school - the purpose of your text is to change what readers think about the world” So simple, so good

One of my all-time favorite talks: how to write so people will care what you have to say. First watched it many years ago and I still think about it constantly. youtu.be/aFwVf5a3pZM

verbally explaining to someone what to click on a screenshare is such a hilariously terrible experience. "click on the button in the top right that says... oh no not that one, move down, one more, oooone more.... ah you skipped it, go back to - oh nope, not quite..."

# avoid the nightmare bicycle

1/ here's a visual model for how AI support makes me better at UI prototyping with the surprising conclusion that AI may *improve* code quality in some specific cases! lets walk thru it step by step...

14/ As the models improve, it's even feeling like the combo is possible sometimes: move faster than ever before, at higher quality. I'm cautious with the super high speeds though: preserving creative agency does require a lot of iteration and pondering the essential problem.

1/ here's a visual model for how AI support makes me better at UI prototyping with the surprising conclusion that AI may *improve* code quality in some specific cases! lets walk thru it step by step...

12/ OK, but what about the UI itself? am I abdicating too much responsibility to the AI? Perhaps. I do worry about this a lot... But I actually think the opposite may be true? I can be more attentive to UI detail when I'm not furiously slinging around code.

1/ here's a visual model for how AI support makes me better at UI prototyping with the surprising conclusion that AI may *improve* code quality in some specific cases! lets walk thru it step by step...

10/ There's a second move I find more subtle and interesting: While maintaining my previous speed of prototyping, I can build at much higher quality.

1/ here's a visual model for how AI support makes me better at UI prototyping with the surprising conclusion that AI may *improve* code quality in some specific cases! lets walk thru it step by step...

8/ From my personal experience, AI *significantly* pushes out the speed-quality frontier for rapidly prototyping web UIs in React. (I mainly use Cursor Composer w/ 3.5-sonnet, plus a smattering of other tools) The question is: what do we do with this power?

1/ here's a visual model for how AI support makes me better at UI prototyping with the surprising conclusion that AI may *improve* code quality in some specific cases! lets walk thru it step by step...

6/ ok, now we're ready to discuss AI. The green line is my extremely scientific estimate of how AI support moves the boundary today.

1/ here's a visual model for how AI support makes me better at UI prototyping with the surprising conclusion that AI may *improve* code quality in some specific cases! lets walk thru it step by step...

4/ But personally... I'm usually out in the 🤠 Wild west of UI prototyping! (I research tools for thought and programming interfaces.) Here there's a min *speed*: try many ideas, discard most. Which implies a quality *ceiling* - no time to engineer perfectly.

1/ here's a visual model for how AI support makes me better at UI prototyping with the surprising conclusion that AI may *improve* code quality in some specific cases! lets walk thru it step by step...

2/ first, some preliminaries before we talk AI: for anyone building software, there's some tradeoff between speed and code quality. (obviously you can work to push the frontier, but the tradeoff exists)

a tiny example of how AI speeds up UI prototyping: just used cursor composer + o3-mini to speed up a huge table with virtualized rendering. took a couple mins, worked on first try. no detour into math puzzles, no searching for a library. keeps me in flow!

still learning how to use reasoning models, but i tried to give a good set of constraints on the answer here, and also made sure to agree on a plan before coding. (helped me catch a possible bug ahead of time!)

pro tip: Claude Projects as executive function assistance i'm dealing with an international bureaucracy thing that's gonna take months... tedious but has to get done so i made a Project with docs explaining the process, now Claude tells me exactly what to do next and helps me do it faster 😎