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
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.
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'm not going to claim I entirely understand the workflow primitives even after a couple reads (does this diagram help? no? no)
But the gist seems to be breaking tasks down into atomic units of work, tracked in git, executed, checked, and merged through a zoo of loops and pre-defined workflows.
But the gist seems to be breaking tasks down into atomic units of work, tracked in git, executed, checked, and merged through a zoo of loops and pre-defined workflows.
January 3, 2026 at 8:53 AM
I'm not going to claim I entirely understand the workflow primitives even after a couple reads (does this diagram help? no? no)
But the gist seems to be breaking tasks down into atomic units of work, tracked in git, executed, checked, and merged through a zoo of loops and pre-defined workflows.
But the gist seems to be breaking tasks down into atomic units of work, tracked in git, executed, checked, and merged through a zoo of loops and pre-defined workflows.
This is utterly unhinged in the best possible way. High praise for running a tour of the plane while it's a quarter-built and mid-flight.
steve-yegge.medium.com/welcome-to-g...
Some choice excerpts.
steve-yegge.medium.com/welcome-to-g...
Some choice excerpts.
January 3, 2026 at 8:30 AM
This is utterly unhinged in the best possible way. High praise for running a tour of the plane while it's a quarter-built and mid-flight.
steve-yegge.medium.com/welcome-to-g...
Some choice excerpts.
steve-yegge.medium.com/welcome-to-g...
Some choice excerpts.
Context windows out to thwart all our beautiful dreams
December 22, 2025 at 5:23 PM
Context windows out to thwart all our beautiful dreams
The body temp feature is also really good at picking up when you're about to get sick / validates when you are sick. Helps me let myself rest and skip workouts.
My sitch of managing new parenthood obvs a bit extreme. But I bet there are useful insights that lean more into optimisation vs. survival
My sitch of managing new parenthood obvs a bit extreme. But I bet there are useful insights that lean more into optimisation vs. survival
December 2, 2025 at 10:10 AM
The body temp feature is also really good at picking up when you're about to get sick / validates when you are sick. Helps me let myself rest and skip workouts.
My sitch of managing new parenthood obvs a bit extreme. But I bet there are useful insights that lean more into optimisation vs. survival
My sitch of managing new parenthood obvs a bit extreme. But I bet there are useful insights that lean more into optimisation vs. survival
It's made a big difference for me over the last 6 months. Being in a time of chronic sleep dep and sickness is a good challenge for it 😅
Helps me figure out how much sleep I've gotten when most nights are split into 5-6 stretches and I have no memory how many times we were up, for how long, etc.
Helps me figure out how much sleep I've gotten when most nights are split into 5-6 stretches and I have no memory how many times we were up, for how long, etc.
December 2, 2025 at 10:10 AM
It's made a big difference for me over the last 6 months. Being in a time of chronic sleep dep and sickness is a good challenge for it 😅
Helps me figure out how much sleep I've gotten when most nights are split into 5-6 stretches and I have no memory how many times we were up, for how long, etc.
Helps me figure out how much sleep I've gotten when most nights are split into 5-6 stretches and I have no memory how many times we were up, for how long, etc.
The new Oura app redesign is so beautiful it’s almost making me feel better about having norovirus.
November 12, 2025 at 8:02 AM
The new Oura app redesign is so beautiful it’s almost making me feel better about having norovirus.
First day of my new life at Github Next! @githubnext.com ✨
I've had my eye on this team for a long time, and it feels like the perfect moment to join them.
I've had my eye on this team for a long time, and it feels like the perfect moment to join them.
October 8, 2025 at 10:58 AM
First day of my new life at Github Next! @githubnext.com ✨
I've had my eye on this team for a long time, and it feels like the perfect moment to join them.
I've had my eye on this team for a long time, and it feels like the perfect moment to join them.
TFW you can't find any software that will let you track map locations connected to structured data in a table in one interface so you have to vibe code it yourself.
Felt, Airtable, etc. were all $100+/month for the right to do this. Lol, nope.
One day of GPT-5 vibe coding and problem solved.
Felt, Airtable, etc. were all $100+/month for the right to do this. Lol, nope.
One day of GPT-5 vibe coding and problem solved.
September 22, 2025 at 2:36 PM
TFW you can't find any software that will let you track map locations connected to structured data in a table in one interface so you have to vibe code it yourself.
Felt, Airtable, etc. were all $100+/month for the right to do this. Lol, nope.
One day of GPT-5 vibe coding and problem solved.
Felt, Airtable, etc. were all $100+/month for the right to do this. Lol, nope.
One day of GPT-5 vibe coding and problem solved.
They do have a culture section and you can personalise the feed to what you're interested in. They could certainly expand how much control users have over topics and sources here, but it's a decent start.
September 11, 2025 at 3:52 PM
They do have a culture section and you can personalise the feed to what you're interested in. They could certainly expand how much control users have over topics and sources here, but it's a decent start.
Feels like the news (mostly) sans short-term, small scale, sensationalist distractions.
I wish the filtering & ranking system was more transparent re: how the system decides what ranks high/low.
There's a write up on the about page (newsminimalist.com/about), but it should be clear in the main UI.
I wish the filtering & ranking system was more transparent re: how the system decides what ranks high/low.
There's a write up on the about page (newsminimalist.com/about), but it should be clear in the main UI.
September 11, 2025 at 3:30 PM
Feels like the news (mostly) sans short-term, small scale, sensationalist distractions.
I wish the filtering & ranking system was more transparent re: how the system decides what ranks high/low.
There's a write up on the about page (newsminimalist.com/about), but it should be clear in the main UI.
I wish the filtering & ranking system was more transparent re: how the system decides what ranks high/low.
There's a write up on the about page (newsminimalist.com/about), but it should be clear in the main UI.
Loving the concept and content on News Minimalist: newsminimalist.com
Using ML to rank news stories by "importance" (scale, impact, novelty, credibility, legacy) and gives you a feed of only high scoring items.
At first glance, better quality than the front page of the BBC, Guardian, or NYT
Using ML to rank news stories by "importance" (scale, impact, novelty, credibility, legacy) and gives you a feed of only high scoring items.
At first glance, better quality than the front page of the BBC, Guardian, or NYT
September 11, 2025 at 3:30 PM
Loving the concept and content on News Minimalist: newsminimalist.com
Using ML to rank news stories by "importance" (scale, impact, novelty, credibility, legacy) and gives you a feed of only high scoring items.
At first glance, better quality than the front page of the BBC, Guardian, or NYT
Using ML to rank news stories by "importance" (scale, impact, novelty, credibility, legacy) and gives you a feed of only high scoring items.
At first glance, better quality than the front page of the BBC, Guardian, or NYT
I've wanted versioning on my digital garden for ages. Felt like a critical missing piece.
Making my own dreams come true over here.
Hard but fun to design this. These aren't automatically generated – I intentionally decide when to make new versions. Not every edit = new version. Only major updates
Making my own dreams come true over here.
Hard but fun to design this. These aren't automatically generated – I intentionally decide when to make new versions. Not every edit = new version. Only major updates
August 14, 2025 at 1:18 PM
I've wanted versioning on my digital garden for ages. Felt like a critical missing piece.
Making my own dreams come true over here.
Hard but fun to design this. These aren't automatically generated – I intentionally decide when to make new versions. Not every edit = new version. Only major updates
Making my own dreams come true over here.
Hard but fun to design this. These aren't automatically generated – I intentionally decide when to make new versions. Not every edit = new version. Only major updates
I found it's easy to prompt ChatGPT and Claude into being more critical. They can be harsh in a good way – the kind of harsh you need when your ideas/work sucks a bit.
But I think this critical character shouldn't be something users have to prompt engineer themselves. It should be easier to access.
But I think this critical character shouldn't be something users have to prompt engineer themselves. It should be easier to access.
August 6, 2025 at 9:39 AM
I found it's easy to prompt ChatGPT and Claude into being more critical. They can be harsh in a good way – the kind of harsh you need when your ideas/work sucks a bit.
But I think this critical character shouldn't be something users have to prompt engineer themselves. It should be easier to access.
But I think this critical character shouldn't be something users have to prompt engineer themselves. It should be easier to access.
Claude 4 Sonnet in Cursor just LOVES giving itself evaluations like OUTSTANDING and PERFECT when it's done implementing something. Complete with effusive details of everything it's achieved.
For features it writes bugs into, it simply grades them: WORKING
For features it writes bugs into, it simply grades them: WORKING
August 4, 2025 at 9:08 AM
Claude 4 Sonnet in Cursor just LOVES giving itself evaluations like OUTSTANDING and PERFECT when it's done implementing something. Complete with effusive details of everything it's achieved.
For features it writes bugs into, it simply grades them: WORKING
For features it writes bugs into, it simply grades them: WORKING
A helpful graph made by @stevekrouse.com on the inverse relationship between vibes and understanding in AI assisted code.
Put a few thoughts down here: maggieappleton.com/2025-08-vibe...
Original article: blog.val.town/vibe-code
Put a few thoughts down here: maggieappleton.com/2025-08-vibe...
Original article: blog.val.town/vibe-code
August 2, 2025 at 12:23 PM
A helpful graph made by @stevekrouse.com on the inverse relationship between vibes and understanding in AI assisted code.
Put a few thoughts down here: maggieappleton.com/2025-08-vibe...
Original article: blog.val.town/vibe-code
Put a few thoughts down here: maggieappleton.com/2025-08-vibe...
Original article: blog.val.town/vibe-code
Starting to get emails from sentient beings living inside Gemini. This is getting fun.
I've never written about "spiritual tooling" but okay cool lol.
I've never written about "spiritual tooling" but okay cool lol.
July 17, 2025 at 6:53 AM
Starting to get emails from sentient beings living inside Gemini. This is getting fun.
I've never written about "spiritual tooling" but okay cool lol.
I've never written about "spiritual tooling" but okay cool lol.
Gemini in Google Colab is a shining example of how *not* to integrate LLMs into a product.
So much potential. Ruined by terrible design.
Giant diffs where I can't accept/reject on a line-by-line basis.
Unclear what context it has.
Can't ref specific cells.
Can't copy/paste code into chat! Wild
So much potential. Ruined by terrible design.
Giant diffs where I can't accept/reject on a line-by-line basis.
Unclear what context it has.
Can't ref specific cells.
Can't copy/paste code into chat! Wild
June 28, 2025 at 9:01 AM
Gemini in Google Colab is a shining example of how *not* to integrate LLMs into a product.
So much potential. Ruined by terrible design.
Giant diffs where I can't accept/reject on a line-by-line basis.
Unclear what context it has.
Can't ref specific cells.
Can't copy/paste code into chat! Wild
So much potential. Ruined by terrible design.
Giant diffs where I can't accept/reject on a line-by-line basis.
Unclear what context it has.
Can't ref specific cells.
Can't copy/paste code into chat! Wild
Nothing says I'm a millennial like routinely referring to my child as a rapidly evolving Squirtle.
June 20, 2025 at 9:31 AM
Nothing says I'm a millennial like routinely referring to my child as a rapidly evolving Squirtle.
Today’s multi-tasking setup: holding sleeping baby, building agents, reading @mikecaulfield.bsky.social ‘s new book “Verified” - all good stuff!
June 12, 2025 at 6:01 PM
Today’s multi-tasking setup: holding sleeping baby, building agents, reading @mikecaulfield.bsky.social ‘s new book “Verified” - all good stuff!
Also this is total overkill for this little feature on my blog, but it's now super cheap n' easy to make one-off test pages and get Cursor to render components in multiple states with various test data.
Would never be bothered to do this myself, but much easier to catch bugs this way.
Would never be bothered to do this myself, but much easier to catch bugs this way.
June 6, 2025 at 10:35 AM
Also this is total overkill for this little feature on my blog, but it's now super cheap n' easy to make one-off test pages and get Cursor to render components in multiple states with various test data.
Would never be bothered to do this myself, but much easier to catch bugs this way.
Would never be bothered to do this myself, but much easier to catch bugs this way.
I have a cursor rule that outlines how I want Cursor to write these docs, where to put them, how to update them: github.com/MaggieApplet...
I have a long, rambling chat w/ Cursor before it writes these
Example of an in-progress one for a ~medium size feature on my site:
github.com/MaggieApplet...
I have a long, rambling chat w/ Cursor before it writes these
Example of an in-progress one for a ~medium size feature on my site:
github.com/MaggieApplet...
June 6, 2025 at 10:18 AM
I have a cursor rule that outlines how I want Cursor to write these docs, where to put them, how to update them: github.com/MaggieApplet...
I have a long, rambling chat w/ Cursor before it writes these
Example of an in-progress one for a ~medium size feature on my site:
github.com/MaggieApplet...
I have a long, rambling chat w/ Cursor before it writes these
Example of an in-progress one for a ~medium size feature on my site:
github.com/MaggieApplet...
Fave Cursor workflow at the moment is get Claude to write feature implementation plans into a markdown document and update it as we go.
Breaks features down into phases with checklists, notes, relevant file lists. Essentially acts as read/write memory to prevent chat context from getting too long.
Breaks features down into phases with checklists, notes, relevant file lists. Essentially acts as read/write memory to prevent chat context from getting too long.
June 6, 2025 at 10:18 AM
Fave Cursor workflow at the moment is get Claude to write feature implementation plans into a markdown document and update it as we go.
Breaks features down into phases with checklists, notes, relevant file lists. Essentially acts as read/write memory to prevent chat context from getting too long.
Breaks features down into phases with checklists, notes, relevant file lists. Essentially acts as read/write memory to prevent chat context from getting too long.