iiinova — where your digital self keeps evolving

Geoffrey Litt @geoffreylitt.com · 22/04/2025

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/

160

Geoffrey Litt @geoffreylitt.com · 22/04/2025

this starts very simple: just check a box to focus down on a subset of the values in your sheet. eg: "if i lease the cheaper car, what might my budget total look like"? but, because we're in an open-ended spreadsheet, it can also get more interesting than that... 4/

140

Geoffrey Litt @geoffreylitt.com · 22/04/2025

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/

160

Geoffrey Litt @geoffreylitt.com · 22/04/2025

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/

4618

Geoffrey Litt @geoffreylitt.com · 23/03/2025

The Deep Research Printer: Say any question, get a custom printed report. The calmness of paper. The meditative quality of *actually reading*, not spawning a million tabs. Combined with the vast knowledge of the Web, answering our most niche curiosities.

2161

Geoffrey Litt @geoffreylitt.com · 20/03/2025

In school why do teachers read your work? “In school… you’re attaching a $100 bill to your paper, handing it to your instructor, and saying hey will you read this…” Seriously just go watch the talk it’s so good

040

Geoffrey Litt @geoffreylitt.com · 20/03/2025

“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

1151

Geoffrey Litt @geoffreylitt.com · 12/02/2025

15/ Anyway, that's the lens I'm finding helpful these days. tldr: in the wild west, speed wins, and AI is fast. So we can thoughtfully apply AI to make better prototypes. If you're using similar techniques would be curious how you think about it.

230

Geoffrey Litt @geoffreylitt.com · 12/02/2025

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.

100

Geoffrey Litt @geoffreylitt.com · 12/02/2025

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.

100

Geoffrey Litt @geoffreylitt.com · 12/02/2025

11/ This is not one sentence prompts. It's long detailed prompts, iteration, code review. In the weeds! I can make a proper plan for how something should work... and then the AI executes it in minutes! So we're still moving fast enough for prototyping.

100

Geoffrey Litt @geoffreylitt.com · 12/02/2025

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.

110

Geoffrey Litt @geoffreylitt.com · 12/02/2025

9/ There's an obvious here: MOVE FAST 🏎️. One sentence prompt, make an app, boom you're done! This makes for fun demos and can be useful for random throwaway tools... But not useful at all when I'm trying to prototype a good UI that hasn't been made before.

110

Geoffrey Litt @geoffreylitt.com · 12/02/2025

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?

120

Geoffrey Litt @geoffreylitt.com · 12/02/2025

7/ Let's first address the 💼 Land of proper engineering. Maybe AI helps you move faster at constant quality? Maybe your codebase turns to slop and things are terrible? Honestly I have no idea! Not the topic here. Let's move on to the wild west where I typically operate.

100

Geoffrey Litt @geoffreylitt.com · 12/02/2025

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.

110

Geoffrey Litt @geoffreylitt.com · 12/02/2025

5/ The thing is...code quality still matters out here! A well-built prototype often provides better signal by holding up to real use, and makes it easier to try out new ideas. I think a lot about surfing the speed/quality tradeoff here and trying to push the boundary.

110

Geoffrey Litt @geoffreylitt.com · 12/02/2025

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.

100

Geoffrey Litt @geoffreylitt.com · 12/02/2025

3/ if you're in the 💼 Land of proper engineering (production engineering), you're gonna impose some minimum quality bar, which in turn imposes a speed limit.

100

Geoffrey Litt @geoffreylitt.com · 12/02/2025

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)

100

Geoffrey Litt @geoffreylitt.com · 12/02/2025

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...

1132

Geoffrey Litt @geoffreylitt.com · 11/02/2025

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!)

110

Geoffrey Litt @geoffreylitt.com · 11/02/2025

when you're tired after a work day, it really helps to have tasks broken down like this:

070

Geoffrey Litt @geoffreylitt.com · 24/01/2025

The latest Cursor Composer + Sonnet is accelerating me to a ridiculous degree these days—I'm feeling ~2-3x faster at executing major code changes. Makes trying new ideas feel so much lighter and worth doing.

2380

Geoffrey Litt @geoffreylitt.com · 03/01/2025

Whole thing took just a few minutes, here are all the prompt. Love that I didn’t need to use some fancy app. Malleable software = does just what I need, and nothing more.

141

Geoffrey Litt @geoffreylitt.com · 03/01/2025

Stuck at a hotel gym with unfamiliar equipment? Obviously ask Claude for a custom workout plan… Oh and one more thing: ask for an entire custom workout app that guides you thru the plan 😎

1201

Geoffrey Litt @geoffreylitt.com · 20/12/2024

step 1 of writing a prolog interpreter: have Claude code me a custom debug utility that can visualize what my interpreter is doing :D already helped me fix so many bugs!

4647

Geoffrey Litt @geoffreylitt.com · 20/12/2024

Q: at what age do you think humans become capable of solving this ARC puzzle? (given the first 3 pairs of grids, figure out the pattern and make the output for the 4th)

14221

Geoffrey Litt @geoffreylitt.com · 10/12/2024

split keyboard? i think you mean keyboard with Breakfast Nook (tm)

51198

Geoffrey Litt @geoffreylitt.com · 08/12/2024

one of the things I find most intriguing about computational media: having lots of stuff lying around in a programmable environment increases the occasions where programming is valuable! analogy: spreadsheets are good at storing numbers, and then once in a while you can reach for a formula

1266

Geoffrey Litt @geoffreylitt.com · 08/12/2024

a beautiful list of goals! (from Chris Hancock's PhD thesis: boxer-project.github.io/boxer-litera...

4608

Geoffrey Litt @geoffreylitt.com · 22/11/2024

I find AI writing edits can be really helpful iff: 1) you have a non-generic prompt, eg a specific style guide 2) you can easily review and reject granular changes www.inkandswitch.com/patchwork/no...

190

Geoffrey Litt @geoffreylitt.com · 22/11/2024

hm, apparently with Apple Intelligence writing tools, you get back a big chunk of rewritten text without any diff view.....? almost find that hard to believe, maybe i'm missing something? diffs are so essential for collab with AI

a screenshot of Apple Pages with an AI rewrite of some paragraphs

2180

Geoffrey Litt @geoffreylitt.com · 31/10/2024

It's currently just one long video on youtube, but this schedule gives a rough map of where to look for your interests...

140

Geoffrey Litt @geoffreylitt.com · 04/05/2023

reading books as a training arena for concentrated thought

4183