I'm not sure that AI is making "cognitive debt" worse, and I'm optimistic that AI can in fact help us mitigate it.
www.natemeyvis.com/on-cognitive...
www.natemeyvis.com/on-cognitive...
On cognitive debt
On cognitive debt
People are talking about cognitive debt, the idea that AI-generated codebases are at risk of falling into a state where nobody knows how...
www.natemeyvis.com
February 15, 2026 at 6:58 PM
I'm not sure that AI is making "cognitive debt" worse, and I'm optimistic that AI can in fact help us mitigate it.
www.natemeyvis.com/on-cognitive...
www.natemeyvis.com/on-cognitive...
What might an AI-first recipe site look like?
Blog post: www.natemeyvis.com/what-might-a...
Site: recipes.natemeyvis.com
Blog post: www.natemeyvis.com/what-might-a...
Site: recipes.natemeyvis.com
What might an AI-first recipe site look like?
The near future will have AI-native versions of just about everything. I want to know more about what that will look like, and I want a clean modern recipe s...
www.natemeyvis.com
February 13, 2026 at 11:18 PM
What might an AI-first recipe site look like?
Blog post: www.natemeyvis.com/what-might-a...
Site: recipes.natemeyvis.com
Blog post: www.natemeyvis.com/what-might-a...
Site: recipes.natemeyvis.com
Programming with AI reminds me a bit of 12-tabling online poker in the early days.
www.natemeyvis.com/new-technolo...
www.natemeyvis.com/new-technolo...
New technology in programming and poker
Work feels different now. Steve Yegge captured something important in an interview with Gergely Orosz:
There’s a vampiric effect with AI, where it gets you ...
www.natemeyvis.com
February 12, 2026 at 10:36 PM
Programming with AI reminds me a bit of 12-tabling online poker in the early days.
www.natemeyvis.com/new-technolo...
www.natemeyvis.com/new-technolo...
Some first thoughts on living in a digital world more of my own making:
www.natemeyvis.com/on-making-on...
www.natemeyvis.com/on-making-on...
On making one's own environment
First, an update on my vibecoding agentic engineering journey:
I'm making approximately one new webapp per day, slightly more over the last week.[^1]
Not a...
www.natemeyvis.com
February 9, 2026 at 11:17 PM
Some first thoughts on living in a digital world more of my own making:
www.natemeyvis.com/on-making-on...
www.natemeyvis.com/on-making-on...
In some circles this is one of my most contrarian views: www.natemeyvis.com/on-having-a-...
On having a data object
Here's a common pattern:
People this pattern. Everyone likes the (apparent) simplicity of , and many engineers also think that those objects bring abs...
www.natemeyvis.com
October 27, 2025 at 8:42 PM
In some circles this is one of my most contrarian views: www.natemeyvis.com/on-having-a-...
Jumping straight into the deep end on a chilly morning for #LearnedLeague 106.
August 18, 2025 at 1:21 AM
Jumping straight into the deep end on a chilly morning for #LearnedLeague 106.
Some thoughts about spaced repetition and scheduling. (Draft: all comments welcome.)
www.natemeyvis.com/notes-on-spa...
www.natemeyvis.com/notes-on-spa...
Nate Meyvis
Nate Meyvis's personal site
www.natemeyvis.com
July 17, 2025 at 1:09 PM
Some thoughts about spaced repetition and scheduling. (Draft: all comments welcome.)
www.natemeyvis.com/notes-on-spa...
www.natemeyvis.com/notes-on-spa...
If anyone out there is knowledgeable about spaced repetition algorithms and willing to read a draft of a blog post, please let me know! I'd be grateful. Solid knowledge of FSRS and its various constants is particularly useful, but not necessary. (DMs are open, etc.)
July 13, 2025 at 9:34 PM
If anyone out there is knowledgeable about spaced repetition algorithms and willing to read a draft of a blog post, please let me know! I'd be grateful. Solid knowledge of FSRS and its various constants is particularly useful, but not necessary. (DMs are open, etc.)
Watching some poker on stream for the first time in probably 6 years. (Just what's available free on YouTube.)
I don't ever play poker these days, but that didn't keep me from having a bunch of opinions about the very first hand I saw. (J9 / 22 / K8) @thinkingpoker.bsky.social
I don't ever play poker these days, but that didn't keep me from having a bunch of opinions about the very first hand I saw. (J9 / 22 / K8) @thinkingpoker.bsky.social
July 13, 2025 at 1:43 AM
Watching some poker on stream for the first time in probably 6 years. (Just what's available free on YouTube.)
I don't ever play poker these days, but that didn't keep me from having a bunch of opinions about the very first hand I saw. (J9 / 22 / K8) @thinkingpoker.bsky.social
I don't ever play poker these days, but that didn't keep me from having a bunch of opinions about the very first hand I saw. (J9 / 22 / K8) @thinkingpoker.bsky.social
Well, bright side, I get to play a significant match on MD25, and if I'm going to be playing to avoid relegation, this is about as safe as it comes (I'm safe with a win or tie, or LegnerB loss or tie, or OvallesJ loss, or HaanD loss [or maybe tie]). #LearnedLeague
March 15, 2025 at 6:38 PM
Well, bright side, I get to play a significant match on MD25, and if I'm going to be playing to avoid relegation, this is about as safe as it comes (I'm safe with a win or tie, or LegnerB loss or tie, or OvallesJ loss, or HaanD loss [or maybe tie]). #LearnedLeague
@cdbarker.bsky.social I'm sure this is a very old observation in APUSH circles, but what are you supposed to do about the start of the Philippine-American War, the Newsboys strike, and so on?
February 23, 2025 at 3:27 PM
@cdbarker.bsky.social I'm sure this is a very old observation in APUSH circles, but what are you supposed to do about the start of the Philippine-American War, the Newsboys strike, and so on?
A good edge case to be in the habit of considering is "what if the back end did nothing but dump all the relevant data to the front end, and the front end did everything else?" Taken literally, it's usually not the best idea, but it's well worth thinking through.
December 24, 2024 at 6:55 PM
A good edge case to be in the habit of considering is "what if the back end did nothing but dump all the relevant data to the front end, and the front end did everything else?" Taken literally, it's usually not the best idea, but it's well worth thinking through.
If your New Year's resolutions will involve learning something, I might be able to help (I've built a spaced repetition system that is ready for alpha users):
www.natemeyvis.com/zippyflash-i...
www.natemeyvis.com/zippyflash-i...
Nate Meyvis
Nate Meyvis's personal site
www.natemeyvis.com
December 24, 2024 at 2:48 PM
If your New Year's resolutions will involve learning something, I might be able to help (I've built a spaced repetition system that is ready for alpha users):
www.natemeyvis.com/zippyflash-i...
www.natemeyvis.com/zippyflash-i...
(Unsurprisingly, ChatGPT is a lot better as a math tutor than a Greek or philosophy tutor.)
Christmas break, day 4: got a little spare time and, in half an hour using ChatGPT as a tutor, made more progress in Galois theory than I previously have in tens of hours of study.
December 24, 2024 at 1:11 PM
(Unsurprisingly, ChatGPT is a lot better as a math tutor than a Greek or philosophy tutor.)
Christmas break, day 4: got a little spare time and, in half an hour using ChatGPT as a tutor, made more progress in Galois theory than I previously have in tens of hours of study.
December 24, 2024 at 1:09 PM
Christmas break, day 4: got a little spare time and, in half an hour using ChatGPT as a tutor, made more progress in Galois theory than I previously have in tens of hours of study.
I had overlooked the obvious: this might just be Cursor itself.
I love Cursor and try to keep up with other genAI-powered coding tools, but haven't explored the natural-language analogues. I just tried ChatGPT's Canvas, and it was promising but buggy and sometimes frustrating.
What's the best "Cursor for natural language" tool?
What's the best "Cursor for natural language" tool?
December 23, 2024 at 2:50 PM
I had overlooked the obvious: this might just be Cursor itself.
I love Cursor and try to keep up with other genAI-powered coding tools, but haven't explored the natural-language analogues. I just tried ChatGPT's Canvas, and it was promising but buggy and sometimes frustrating.
What's the best "Cursor for natural language" tool?
What's the best "Cursor for natural language" tool?
December 22, 2024 at 7:56 PM
I love Cursor and try to keep up with other genAI-powered coding tools, but haven't explored the natural-language analogues. I just tried ChatGPT's Canvas, and it was promising but buggy and sometimes frustrating.
What's the best "Cursor for natural language" tool?
What's the best "Cursor for natural language" tool?