Geoffrey Litt

Is Notion a company making "AI coding software" these days? If you want to learn more about Geoffrey I suggest browsing through https://www.geoffreylitt.com/#projects - I've been following his work for a few years, "UI prototyper" is him under-selling himself.

Reminds me of this: https://www.geoffreylitt.com/2025/07/27/enough-ai-copilots-we-need-ai-… I think this is such a great reframing. It makes so much sense; I need an AI that acts more as a HUD and gives me superpowers, not just a copilot that can tell me when I've misspelled a word.

https://worrydream.com https://macwright.com/ https://www.petemillspaugh.com/ https://www.geoffreylitt.com/ https://maggieappleton.com/ https://www.robinsloan.com/ https://thesephist.com/ https://wattenberger.com/ http://conal.net/ https://www.todepond.com/ https://devonzuegel.com/ https://nadia.xyz/ https://adamwiggins.com/ http://glench.com/ https://ncase.me/ Classic from my old Haskell professor: https://byorgey.wordpress.com/2009/01/12/abstraction-intuition-and-the…

This feels very related to the larger research project of “malleable software” that lets everyday people modify and author the software they use for their own needs: https://malleable.systems/ My friend Geoffrey Litt is heading the malleable software group at Ink and Switch: https://www.geoffreylitt.com/

"We propose that web sites can be similarly augmented with other sophisticated data-centric functionality, giving users new benefits over the existing Web." - gonna check this paper out! Reminds me also of this amazing project that also deals in structured data and tables: https://www.geoffreylitt.com/wildcard/

If you're looking for more concrete details on what it's actually like to make things at Dynamicland, I recommend this writeup by Omar Rizwan. (from 2018, so doesn't reflect recent progress, but it's still helpful for getting a feel for the place): https://omar.website/posts/notes-from-dynamicland-geokit/ I also wrote a short explanation of some little experiments I did there when I visited a couple years ago: https://www.geoffreylitt.com/projects/dynamicland.html

Could one be able to upscale the video with a GAN like the following example? https://www.geoffreylitt.com/images/article_images/enhance/gan-trainin…

That's a great question. And I completely agree. It's become extremely common to obfuscate client code or throw together 5 NPM packages into a frontend framework to justify "rapid development". Here are a few websites that have great UX and readable source code. For each, you can view source and understand how the page is structured, styled and made interactive: - https://tour.gleam.run, interactive code tutorial - https://sivers.com, ecommerce - https://www.geoffreylitt.com, personal website I enjoy doing this and have recreated a few projects that I liked by reading their source: - https://sudoku-aj.netlify.app inspired by https://sudoku.com - https://imgbar.pages.dev inspired by https://imgflip.com - https://logo-lang.pages.dev inspired by https://www.transum.org/software/Logo Web technologies are amazing. It's one thing to say that it's hard because you're not familiar with it and another that they are objectively bad. I disagree with the second statement. If people want a drag and drop solution for building UIs that's great. I'm sure no-code solutions exist for that. Again, my disagreement is on the point that somehow building UIs with Python is better.

Not a promo — just sharing our design rationale for ArcSphere and why we went with an AI HUD over a Copilot model. I recently read the article “Enough AI copilots! We need AI HUDs,” and it resonated deeply with me. It perfectly echoes the design principles I’ve been exploring for months with ArcSphere, our AI-native browser. https://www.geoffreylitt.com/2025/07/27/enough-ai-copilots-we-need-ai-…

I want a link to the GitHub for this[0] which he linked to. Makes Prolog quite interesting. [0]: https://www.geoffreylitt.com/2024/12/22/making-programming-more-fun-wi…

> a consistent path to interacting with the world e.g sms, mail, weather, social, etc. Here's an interesting toy-project where someone hooked up agents to calendars, weather, etc and made a little game interface for it. https://www.geoffreylitt.com/2025/04/12/how-i-made-a-useful-ai-assista…

Also your two year old post, Malleable software in the age of LLMs, https://www.geoffreylitt.com/2023/03/25/llm-end-user-programming.html

For people who want more examples of this “vibe”, here’s a tiny subset of places / people / projects to check out: https://futureofcoding.org/catalog/ https://cristobal.space/writing/folk-computer.html https://dynamicland.org/ https://www.inkandswitch.com/local-first/ https://www.geoffreylitt.com/ https://maggieappleton.com/folk-interfaces

Interesting approach to spreadsheets. Reminds me a bit of Geoffrey Litt's projects: https://www.geoffreylitt.com/wildcard/

There's a research project at MIT trying to do this - https://www.geoffreylitt.com/wildcard/salon2020/

You can enhance the overall image quality using: https://github.com/alexjc/neural-enhance on every frame. https://letsenhance.io/ For faces: https://www.geoffreylitt.com/2017/06/04/enhance-upscaling-images-with-…

Yes, there is value in memorizing things, as things in our memory are easier to work with for thinking than things we have to go out, search for, access, and then get into our memory. See for example Barbara Oakley's discussion on mathematical fluency: nautil.us/issue/40/learning/how-i-rewired-my-brain-to-become-fluent-in-math-rp Or Feynman on the need for mathematical fluency to do physics: > What we have to do is to learn to differentiate like we know how much is 3 and 5, or how much is 5 times 7, because that kind of work is involved so often that it’s good not to be confounded by it. When you write something down, you should be able to immediately differentiate it without even thinking about it, and without making any mistakes. You’ll find you need to do this operation all the time—not only in physics, but in all the sciences. Therefore differentiation is like the arithmetic you had to learn before you could learn algebra. > Incidentally, the same goes for algebra: there’s a lot of algebra. We are assuming that you can do algebra in your sleep, upside down, without making a mistake. We know it isn’t true, so you should also practice algebra: write yourself a lot of expressions, practice them, and don’t make any errors. Of course, in this particular discussion re: javascript, I think the design of the language doesn't help much here. Consider Javascript's `Date`, which the OP calls out as an API with a particularly difficult to remember set of conventions. Authors of…

http://computationalculture.net/rss https://2019.wattenberger.com/rss https://austinhenley.com/blog/feed.rss https://blog.ouseful.info/feed https://jakelazaroff.com/rss.xml https://joshmpollock.com/feed.xml https://lilianweng.github.io/index.xml https://maggieappleton.com/rss.xml https://runzhe-yang.science/feed.xml https://thereader.mitpress.mit.edu/feed/ https://thesephist.com/index.xml https://topos.site/blog/index.xml https://www.geoffreylitt.com/feed.xml

From https://ohmjs.org — Here are some awesome things people have built using Ohm: - Shopify's theme-tools (https://github.com/Shopify/theme-tools/), used in their online code editor and the official VS code extension. - Seymour (https://github.com/harc/seymour), a live programming environment for the classroom. - Shadama (https://tinlizzie.org/~ohshima/shadama2/live2017/), a particle simulation language designed for high-school science. - Slang (http://slang.kylestetz.com/), a browser-based audio programming language, and turtle.audio, a music sequencer inspired by turtle graphics programming. - Simpletalk (https://github.com/dkrasner/Simpletalk) is an expressive, programmable authoring system inspired by Hypercard and Smalltalk. (See also the StrangeLoop talk). - Wildcard (https://www.geoffreylitt.com/wildcard/), a browser extension that empowers anyone to modify websites to meet their own specific needs, uses Ohm for its spreadsheet formulas. - JAMScript (https://citelab.github.io/JAMScript/) is a programming language for edge-based IoT applications. - Bruno (https://github.com/usebruno/bruno) is an open source IDE for exploring and testing APIs. It has also been used in a number of projects by Ink & Switch (https://inkandswitch.com), including Potluck (Dynamic documents as personal software: https://www.inkandswitch.com/potluck/), the Deja Vu project at MIT (https://sdg.csail.mit.edu/project/deja-vu/), ...