kamens

I used to do this and called it "Coding with AI the Hard Way" in a nod to Zed Shaw: https://kamens.com/blog/code-with-ai-the-hard-way

I no longer do and blogged my updates for fear of being seen as a luddite:

https://kamens.com/blog/code-with-ai-the-hard-way-update https://kamens.com/blog/code-with-ai-the-hard-way-update-ii

Same situation here. Dropping to 4.7 for now.

this is beautiful

I love this. It needs to exist because it's fun.

Personalized educational activity (real, physical) books: https://elbobooks.com

^^ project with my daughter

Parallel agents debate your ideas/work: https://murderboards.ai

^^ solo project / code review agents for non-coders / inspired by Compound Engineering plugin’s code review flow

You, Thomas, Watsi, and crew have been an inspiration for a long time. I loved getting to know you all back in the day, and I've loved being a small donor since the early days. Deep respect for what you built.

i'm torn between my stupidity re:your first comment and my love of eliminating pinch points (now you're speaking my language). i need to read up a lot to better understand your suggestion!

(most pinch points are gone these days, it just required a lot of edge case hunting)

thank you! we've generated ~600 crazy unique mazes for kids so far, kinda want to make a gallery

The main difference between the above tool and most custom shaped maze generators out there is breaking the assumption that the maze's outer shape must be defined by adding or removing regularly-shaped cells along the edge.

To have mazes look more human drawn, cells need to be irregular and the inner walls need naturally follow the contours of the outer shape.

I used Jamis' book extensively to build this AI tool for generating custom mazes of any shape! https://kamens.com/blog/generating-custom-mazes-with-ai

Same question to you: did you read his blog and arguments in detail?

Further, he didn't just make multiple contrarian predictions in the hope he'd be credited -- he had a way of making predictions in ways that could be interpreted multiple ways later.

I both (A) found this infuriating and (B) found his understanding of what Trump is to be deeply insightful.

I agree with you trymas! I myself spent time cataloguing a number of his predictions that did not come true.

I am still asking a specific question: for the prediction of Trump's rise, did the critics downvoting me read his actual writing and arguments? It was not a single contrarian prediction. It was an extended, thoughtful, and informed perspective that has helped understand the world for the past 10 years.

Genuine question: did you read his blog and arguments in detail?

The minimum recognition Scott Adams deserves should be having updated the world model of those who read his blog.

It is hard to remember how thoroughly Trump's presidential run was seen as a joke in 2015. I bet most people can't remember and somehow think they always knew Trump stood a real chance. That is likely a lie.

Scott made specific, reasoned, unique arguments about why Trump would win, with high conviction. This was at a time when it was about as non-consensus and unpopular as possible to do so (it wasn't just that people didn't want Trump to win, there was a complete dismissal of the possibility from both sides of the aisle).

The fact that Scott was right, and continued to be right when forecasting much about politics, taught me a lot about the nature of the world we live in. Scott clearly understood something important that I did not at the time.

I agree. There’s another guy (in the quote tweet) here who’s pushed on Where’s Waldo stuff, but like you I think it’s currently stuck at the “deformed bodies/faces” issue: https://x.com/kamens/status/2001396716654727607

I also suspect it may be solvable by switching to something other than humans - we probably won’t be as weirded out by malformed cars or plants or whatever.

You just reminded me about my math teacher letting us use programs on our TI-83 to cheat on the test if we could type the programs in ourselves. Definitely worked

The hard way solves this for me / I still get to vibe as much as I want: https://kamens.com/blog/code-with-ai-the-hard-way

I love this TODO approach not just for what it does for future readers as Sophie notes but also for the mental release it gives me when thinking about edge cases that I don't want to commit to fixing.

PS Hi Sophie!

Personally, I follow the simple rule: "I type every single character myself. The AI/agent/etc offers inspiration." It's an effective balance between embracing what the tech can do (I'm dialing up my usage) and maintaining my personal connection to the code (I'm having fun + keeping things in my head).

I wrote about it: https://kamens.com/blog/code-with-ai-the-hard-way

Fun idea!

Building on that: there's a common children's magic trick involving a flip book that magically "colors" its pages (https://www.magicinc.net/products/fun-magic-coloring-book?va...)

It works by moving your thumb to a different position while flipping the pages -- every Xth page is cut at slightly different lengths, so when you move your thumb to the next position, different pages become visible during the flip

Using this trick you could show multiple different video clips in the flipbook just by moving your thumb to a different spot

Josh your work is amazing

fellow t1d + engineer + competitive rower (20 years ago...sigh) here.

props on shipping an incredible personal project! if you ever want to geek out about diabetes tech, DM me on X @kamens

scott hanselman would probably also love to chat about your project

for those who don't know diabetes, this would be like publishing an article titled "Dementia risk soars for adults who repeatedly slammed their head into a wall as a child"

...and doesn't clarify that the study has absolutely nothing to do with alzheimer's / is only talking about blunt force trauma-induced damage

the diseases, their effects, their causes, and their treatments are dramatically different