Maggie Appleton
@maggieappleton.com
Design engineer playing with AI and hacky prototypes @githubnext.com
Adores digital gardening, end-user development, and embodied cognition. Makes visual essays about design, programming, and anthropology.
📍 London
🌱 maggieappleton.com
Adores digital gardening, end-user development, and embodied cognition. Makes visual essays about design, programming, and anthropology.
📍 London
🌱 maggieappleton.com
Nice - I’ll take a look. Although I think most of my design ideas are too non-standard for any library to work for me. I just like making things at the intersection of illustration x data vis x diagram. I think feeding Claude sketches ahead of time and fixing by hand is the workflow for a while…
January 13, 2026 at 11:21 AM
Nice - I’ll take a look. Although I think most of my design ideas are too non-standard for any library to work for me. I just like making things at the intersection of illustration x data vis x diagram. I think feeding Claude sketches ahead of time and fixing by hand is the workflow for a while…
Yeah I thought this too – that starting with mediocre, predictable stuff narrows the range of exploration substantially.
We can ward this off a bit by having high standards and/or a specific vision for the final result pre-prompting. There's a tradeoff calc here: easier/faster but slightly worse
We can ward this off a bit by having high standards and/or a specific vision for the final result pre-prompting. There's a tradeoff calc here: easier/faster but slightly worse
January 13, 2026 at 7:38 AM
Yeah I thought this too – that starting with mediocre, predictable stuff narrows the range of exploration substantially.
We can ward this off a bit by having high standards and/or a specific vision for the final result pre-prompting. There's a tradeoff calc here: easier/faster but slightly worse
We can ward this off a bit by having high standards and/or a specific vision for the final result pre-prompting. There's a tradeoff calc here: easier/faster but slightly worse
Yeah I'm having trouble spotting obvious errors in this, based on my fuzzy memory of the social system from year 6...
January 13, 2026 at 7:21 AM
Yeah I'm having trouble spotting obvious errors in this, based on my fuzzy memory of the social system from year 6...
Yeah it's probably a smaller model. I don't have Gemini Pro and just used whatever the default setting is on the web chat interface.
January 13, 2026 at 7:19 AM
Yeah it's probably a smaller model. I don't have Gemini Pro and just used whatever the default setting is on the web chat interface.
I'm thinking like: gestalt principles translated into clear rules (put related items <8px apart, put other items >32px apart), grid system, when connecting two items verify your lines are touching the edges, etc.
Mermaid was suggested a bunch in this thread but for me its too constrained and ugly.
Mermaid was suggested a bunch in this thread but for me its too constrained and ugly.
January 12, 2026 at 9:56 AM
I'm thinking like: gestalt principles translated into clear rules (put related items <8px apart, put other items >32px apart), grid system, when connecting two items verify your lines are touching the edges, etc.
Mermaid was suggested a bunch in this thread but for me its too constrained and ugly.
Mermaid was suggested a bunch in this thread but for me its too constrained and ugly.
Oh man a grid constraint is a good idea! This is the first time I've tried prompting diagrams in earnest and gotten promising results (attempts ~6 months ago were too crap to even entertain, lol)
I'll try building out a Claude skill for it - some mix of tight instructions and verification loops
I'll try building out a Claude skill for it - some mix of tight instructions and verification loops
January 12, 2026 at 9:53 AM
Oh man a grid constraint is a good idea! This is the first time I've tried prompting diagrams in earnest and gotten promising results (attempts ~6 months ago were too crap to even entertain, lol)
I'll try building out a Claude skill for it - some mix of tight instructions and verification loops
I'll try building out a Claude skill for it - some mix of tight instructions and verification loops
Using Claude because I need these to be in working code – SVG, CSS, HTML, JS. It allows me to have have fine-grained control over details. And I usually add in animations and interactions, plus I need them to be responsive for mobile.
Nano banan still has a ways to go 😄 bsky.app/profile/magg...
Nano banan still has a ways to go 😄 bsky.app/profile/magg...
I hadn't tried out Nano Banana for diagrams yet so I had a little play. Wonderfully promising and hilariously crap in the details. So close and yet so far.
January 12, 2026 at 9:44 AM
Using Claude because I need these to be in working code – SVG, CSS, HTML, JS. It allows me to have have fine-grained control over details. And I usually add in animations and interactions, plus I need them to be responsive for mobile.
Nano banan still has a ways to go 😄 bsky.app/profile/magg...
Nano banan still has a ways to go 😄 bsky.app/profile/magg...
I hadn't tried out Nano Banana for diagrams yet so I had a little play. Wonderfully promising and hilariously crap in the details. So close and yet so far.
January 12, 2026 at 9:42 AM
I hadn't tried out Nano Banana for diagrams yet so I had a little play. Wonderfully promising and hilariously crap in the details. So close and yet so far.
SVG and CSS. I gave it some existing examples from my blog and style files (global CSS vars, etc.). Plus some guidelines: be subtle, use soft shadows and round borders, use these colours
Agree it's not bad as a starting point. And seeing what I dislike helps me take it in a better direction.
Agree it's not bad as a starting point. And seeing what I dislike helps me take it in a better direction.
January 11, 2026 at 11:27 AM
SVG and CSS. I gave it some existing examples from my blog and style files (global CSS vars, etc.). Plus some guidelines: be subtle, use soft shadows and round borders, use these colours
Agree it's not bad as a starting point. And seeing what I dislike helps me take it in a better direction.
Agree it's not bad as a starting point. And seeing what I dislike helps me take it in a better direction.
It's OpenCode! It's delightful. With the theme catppuccin-macchiato. Also using Ghostty for my terminal and have same theme set there.
January 11, 2026 at 11:22 AM
It's OpenCode! It's delightful. With the theme catppuccin-macchiato. Also using Ghostty for my terminal and have same theme set there.
Oh I didn't know it was customisable at all! I'll take a look. Maybe models will be better at generating initial ideas with a more structured language like that, and I can work off it
January 11, 2026 at 11:20 AM
Oh I didn't know it was customisable at all! I'll take a look. Maybe models will be better at generating initial ideas with a more structured language like that, and I can work off it
My theory here is the major labs have done very little or no RLHF on visual explanations and diagrams? Seems like a blind spot. Image generation alone or text generation alone are very well optimised but the combination seems uniquely hard for current models.
January 11, 2026 at 11:15 AM
My theory here is the major labs have done very little or no RLHF on visual explanations and diagrams? Seems like a blind spot. Image generation alone or text generation alone are very well optimised but the combination seems uniquely hard for current models.
The best diagram outputs an LLM can get to are still crap by my standards. It helps speed me up a bit and give me starting points, but it's still disappointing that their visual reasoning and graphic design skills are really weak.
The layouts and visual language are always predictably boring too
The layouts and visual language are always predictably boring too
January 11, 2026 at 11:13 AM
The best diagram outputs an LLM can get to are still crap by my standards. It helps speed me up a bit and give me starting points, but it's still disappointing that their visual reasoning and graphic design skills are really weak.
The layouts and visual language are always predictably boring too
The layouts and visual language are always predictably boring too
Yeah I've used mermaid diagrams before, but my understand is they're very simple and standardised?
The final output I'm going for with is pretty refined. These are SVG diagrams for one of my essays so I need a lot of control over the visual aesthetics. And I usually add in animation and interaction
The final output I'm going for with is pretty refined. These are SVG diagrams for one of my essays so I need a lot of control over the visual aesthetics. And I usually add in animation and interaction
January 11, 2026 at 11:10 AM
Yeah I've used mermaid diagrams before, but my understand is they're very simple and standardised?
The final output I'm going for with is pretty refined. These are SVG diagrams for one of my essays so I need a lot of control over the visual aesthetics. And I usually add in animation and interaction
The final output I'm going for with is pretty refined. These are SVG diagrams for one of my essays so I need a lot of control over the visual aesthetics. And I usually add in animation and interaction
Claude's second attempt at fixing some of the problems, with a lot of additional steering from me on improving the visual details.
It's still unable to make an arrow go where it needs to, or make two elements connect with a line.
But it's a decent starting point - enough for me to cleanup by hand.
It's still unable to make an arrow go where it needs to, or make two elements connect with a line.
But it's a decent starting point - enough for me to cleanup by hand.
January 11, 2026 at 11:07 AM
Claude's second attempt at fixing some of the problems, with a lot of additional steering from me on improving the visual details.
It's still unable to make an arrow go where it needs to, or make two elements connect with a line.
But it's a decent starting point - enough for me to cleanup by hand.
It's still unable to make an arrow go where it needs to, or make two elements connect with a line.
But it's a decent starting point - enough for me to cleanup by hand.
Figuring out a workflow to make Claude better at creating diagrams and illustrated explanations.
By default it is pretty crap - see this example. Labels overlap. Arrows in the wrong place. Text too small.
But it's also decent at identifying what's wrong once it takes a screenshot.
By default it is pretty crap - see this example. Labels overlap. Arrows in the wrong place. Text too small.
But it's also decent at identifying what's wrong once it takes a screenshot.
January 11, 2026 at 11:04 AM
Figuring out a workflow to make Claude better at creating diagrams and illustrated explanations.
By default it is pretty crap - see this example. Labels overlap. Arrows in the wrong place. Text too small.
But it's also decent at identifying what's wrong once it takes a screenshot.
By default it is pretty crap - see this example. Labels overlap. Arrows in the wrong place. Text too small.
But it's also decent at identifying what's wrong once it takes a screenshot.
I fully support ignoring a lot of what’s happening in agent hype town if it’s doesn’t speak to you. The hype will hype either way. Other useful and interesting work needs to be done in software outside of the hot new thing. Work that is likely being ignored/abandoned as people jump on the bandwagon
January 4, 2026 at 9:18 PM
I fully support ignoring a lot of what’s happening in agent hype town if it’s doesn’t speak to you. The hype will hype either way. Other useful and interesting work needs to be done in software outside of the hot new thing. Work that is likely being ignored/abandoned as people jump on the bandwagon
It's so hard to keep abreast of what's possible with models at the moment. I definitely suggest playing with Claude Code, Codex, & Gemini to develop your own felt sense of where we're at. Even just toy projects or personal benchmarks. They'll both surprise you and face plant. But in interesting ways
January 3, 2026 at 1:27 PM
It's so hard to keep abreast of what's possible with models at the moment. I definitely suggest playing with Claude Code, Codex, & Gemini to develop your own felt sense of where we're at. Even just toy projects or personal benchmarks. They'll both surprise you and face plant. But in interesting ways
A little January update: I am very tired, overwhelmed by all the agents, eating too many hobnobs, and willing myself back into the mindset of someone who knows how to research and write useful things.
maggieappleton.com/now-2026-01
maggieappleton.com/now-2026-01
January 2026 | Maggie Appleton
Maggie's digital garden filled with visual essays on programming, design, and anthropology
maggieappleton.com
January 3, 2026 at 1:22 PM
A little January update: I am very tired, overwhelmed by all the agents, eating too many hobnobs, and willing myself back into the mindset of someone who knows how to research and write useful things.
maggieappleton.com/now-2026-01
maggieappleton.com/now-2026-01
Ha! It is near impossible to make the overton window inside the bubble seem reasonable to everyone outside it
January 3, 2026 at 11:05 AM
Ha! It is near impossible to make the overton window inside the bubble seem reasonable to everyone outside it
I hadn't encountered much of Yegge before so this was quite the onboarding
January 3, 2026 at 11:04 AM
I hadn't encountered much of Yegge before so this was quite the onboarding
Thank you ❤️
Rereading it this morning I realise it sounds like I am *very* tired 😅 which I am, but also very excited and full of the good things in life as well.
Writing it helped me unclench a bit and just start putting some thoughts down. But I will keep up the chocolate hobnob intake levels.
Rereading it this morning I realise it sounds like I am *very* tired 😅 which I am, but also very excited and full of the good things in life as well.
Writing it helped me unclench a bit and just start putting some thoughts down. But I will keep up the chocolate hobnob intake levels.
January 3, 2026 at 11:04 AM
Thank you ❤️
Rereading it this morning I realise it sounds like I am *very* tired 😅 which I am, but also very excited and full of the good things in life as well.
Writing it helped me unclench a bit and just start putting some thoughts down. But I will keep up the chocolate hobnob intake levels.
Rereading it this morning I realise it sounds like I am *very* tired 😅 which I am, but also very excited and full of the good things in life as well.
Writing it helped me unclench a bit and just start putting some thoughts down. But I will keep up the chocolate hobnob intake levels.
...and language is a poor medium for designing easing curves and aesthetic feelings. I always need to touch the code, and it's often faster to CSS than prompt.
FE requires constant human-in-the-loop checks so even if you have a dozen agents working, I am the bottleneck. Scale isn't that helpful.
FE requires constant human-in-the-loop checks so even if you have a dozen agents working, I am the bottleneck. Scale isn't that helpful.
January 3, 2026 at 9:02 AM
...and language is a poor medium for designing easing curves and aesthetic feelings. I always need to touch the code, and it's often faster to CSS than prompt.
FE requires constant human-in-the-loop checks so even if you have a dozen agents working, I am the bottleneck. Scale isn't that helpful.
FE requires constant human-in-the-loop checks so even if you have a dozen agents working, I am the bottleneck. Scale isn't that helpful.
I'm in fruitful debates with colleagues over projects like this. Namely: how much hands-on access to code do we think developers will need in the next generation of tools? How close does it need to be?
I'm in the code-must-be-close camp, at least for the next 2 years. My bias is I do front-end...
I'm in the code-must-be-close camp, at least for the next 2 years. My bias is I do front-end...
January 3, 2026 at 9:02 AM
I'm in fruitful debates with colleagues over projects like this. Namely: how much hands-on access to code do we think developers will need in the next generation of tools? How close does it need to be?
I'm in the code-must-be-close camp, at least for the next 2 years. My bias is I do front-end...
I'm in the code-must-be-close camp, at least for the next 2 years. My bias is I do front-end...