Staff Research Engineer at @GitHubNext. But actually a designer. Writes about design, dev, & anthropology. Also on Bluesky 🦋 @maggieappleton.com

London, England
Maggie Appleton retweeted
Can you understand this snippet of code? Geoffrey Litt discusses Margin Notes:
1
3
19
1,917
I've always wanted my own WYSIWYG editor for my website, and now I have one! Works locally, saves changes to MDX. But the better part is building semantic writing tools on top. Colour-coded sentence classification, flagging cliches, repetition, and claims that need citations
17
11
274
7,459
Classifications ofc done with Jev + agents to respond to in context chat and suggestion alternatives. Still some rough edges (lagging hover states on those classifier popovers are annoying) but it's feeling good. Mostly magical to write in the same format it'll publish in
2
1
11
880
Jigs very good for tweaking design system values with live previews of how those colours work in the context of specific components and WCAG contrast calculators on screen. So easy to say "show me every component that uses grey 400 and put it in the lab file" → tweak → commit
11
4
109
10,326
Maggie Appleton retweeted
people arguing that AI won't get access to wet labs Anthropic:
Replying to @AnthropicAI
This is the first result from our new molecular biology lab, where a team of Anthropic biologists is using Claude to explore and accelerate fundamental biology research. There, Claude works through data and literature to generate hypotheses and candidate biological systems to study. After our scientists review Claude’s hypotheses, they test the most promising ideas, with all lab work done by our scientists. We’d like to extend this approach to a broad range of problems—in genomics and in other fields. If you have a proposal for a research question, we’d like to hear from you.
6
10
359
7,122
For people new to design jigs, this is a good example of using them in the wild. I first saw them used by @doctorbaytas in this beautiful talk at @meetgranola: piped.video/watch?v=t57p7ARE…
added a little bit of spice to the bookmark animation, opus 5.5 btw
9
17
428
45,836
The current state of agent design skills
7
5
132
6,840
Had a wonderful chat with @GergelyOrosz - always nice to go deep on ideas in a proper long chat. Got to show off some notebook sketches and design jigs with agents too.
What can us, engineers else learn from designers and design engineers? Turns out there’s lots, based on talking with one of the best design engineers in the industry, @Mappletons. Timestamps: 00:00 Intro 03:24 From anthropology to tech 10:18 What does a designer do? 18:23 How Maggie works 24:55 The case for planning with physical tools 31:53 Why Maggie is learning woodworking 33:13 Design engineers and engineering constraints 38:49 How Maggie uses Figma 40:30 Design at GitHub Next 45:12 How has AI changed design 50:37 When models design and why humans are still needed 53:30 UX and UI 58:29 Capability gaslighting 1:00:33 One Developer, Two Dozen Agents, Zero Alignment 1:07:21 Craft and AI tells 1:14:17 Visual gardens, home-cooked software, and barefoot developers 1:21:02 Advice for engineers and lessons from anthropology 1:25:34 Book recommendation Brought to you by: • @turbopuffer – a vector and full-text search engine built on object storage. It’s fast, cheap, and extremely scalable. turbopuffer.com/pragmatic • @AntithesisHQ – verify your system’s correctness without human review or traditional integration tests – and avoid bugs or outages. antithesis.com/pragmatic • @EntireHQ – every agent prompt, tool call, stored in your repo, and mirrored. Set up with one click: entire.io/pragmatic Hope you enjoy this unusually visual episode - thanks again, Maggie!
8
23
341
28,890
Maggie Appleton retweeted
BREAKING It has been 30 entire minutes since a frontier model dropped. Experts confirm progress has officially stalled.
3
10
2,168
Maggie Appleton retweeted
Tomorrow on the podcast - with one of the best design engineers I know!
17
6
380
32,841
Maggie Appleton retweeted
Replying to @Mappletons
current jev can be called a decision model, but I don't think the shape should be called that it would be like calling InstructGPT a copywriting model HINT HINT HINT the only alternatives to system one I like: - machine-native model - large programmatic model
25
7
180
16,576
Can we agree to call Jev a "Decision Model"? I feel like they buried this in the explainations and docs. Language models output language. Decision models output decisions.
48
12
302
79,988
Maggie Appleton retweeted
Messing around with @typesafeai Jev for real-time styling 🔤 🔜 🎨 If you can define a bounded, semantically meaningful property space, you can project a natural language expression into that space in one generation step
3
14
218
12,578
Remember that brief period of history when we had to pay for Photoshop? The bit in-between everyone having a bootlegged version, but before coding agents enabled someone was able to recreate all the important parts of Photoshop in an open source product? What a dark time.
I built a Photoshop-like image editor. It’s called Compositor. robbietilton.com/compositor I originally built it for myself to get off my Adobe subscription, but decided to release it for free and make it open source. It has all the essential tools I need for compositing, with none of the BS. I know this workflow is kind of archaic in 2026, but I’m still using it until AI can actually get pixel-perfect on some of the details. The entire app is 12MB. Photoshop is 6,455MB on my machine.
27
7
335
36,145
As someone who earned all their design chops in bootlegged Photoshop and Illustrator in high school, it is almost emotional looking at Compositor and how good it is. It's quality editing software for free. So much is possible for the next gen of designers.
1
22
1,712
Maggie Appleton retweeted
Jev is the future
131
264
4,984
1,126,018
Maggie Appleton retweeted
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
4,038
8,290
76,427
39,767,824
I’m finally doing Design Engineering night at Granola. Come hang out! I love this meetup. Always high quality talks by people with wild ideas
Design Engineering Night #10 is happening on 15 October at Granola HQ. Speakers (absolute legends): • @Mappletons, Design Engineer, @GitHubNext • @vladmoroz, Product Designer, @paper • @alex_barashkov, CEO, PixelPoint Come join us. It’s gonna be fun. RSVP in the reply 👇
10
1
93
8,080