Tuesday, April 14, 2026

Art You Can Only See When Your Vision Is Bad

When I was a kid, sometimes I'd take my glasses off and a pile of laundry would look like a witch. But there was this alphabet poster on my wall that (*without glasses) looked like a cowboy. So I would look at it and imagine he was keeping me safe.

I never forgot that cowboy.

Now I'm making art that works the same way. The plan is to have a show in a gallery where you walk in and take a vision exam like this:

If you have good vision then the smaller letters are unreadable. But here's what it looks like with  blurry vision (specifically uncorrected refractive error, if you have an astigmatism it might not work so well sorry):

If you "fail" the eye test, we hand you a pair of glasses that will blur your vision enough so you can appreciate the art too.

Here's a poem. To read it, take your glasses off and go back and forth until you start to see gaps between the words; then go more slowly until you see the letters. If you have a camera 📷 you can set your lens to manual focus and deliberately defocus it until the poem appears.

I'm also working on a bit more artistic drawings that should have a more robust effect that works even for folks with astigmatisms or other types of lens error:

Still a work in progress - so stay tuned for updates!

Wednesday, April 08, 2026

Due to Overwhelming Demand From Our Zero Customers, the Hieroglyphics Generator Has Been Improved

Generate genuinely new hieroglyphic inscriptions with GlyphGPT


Sample hieroglyphic output

The people have spoken. Well — not actual people. Nobody emailed, DMed, or sent a carrier pigeon demanding better hieroglyphics. But I could feel the disappointment radiating from our estimated zero active users every time the model spat out malformed gibberish.

So I fixed it.... Or Claude did...

Using autoresearch running on Google Colab GPUs, the model saw a 43% improvement across 89 automated experiments in about 8 hours. The old model? Honestly, most of its output was nonsense. The new one almost always translates to something reasonable:

EgyptGPT Autoresearch: 89 experiments in 7.4 hours

Our zero customers are thrilled.

The technical challenge: getting autoresearch to run on Colab

This was the real puzzle. Colab's default security settings block Claude's code tool from running properly. And if the GPU session shuts down — which it does, because Colab is temporary — it forgets its own research history.

I fixed this with a Google Drive rsync loop that saves learnings from both good and bad experiments, plus an extra step to commit the good code to GitHub.

One funny moment: I interrupted the research flow to check on progress and Claude seemed genuinely annoyed, then started right back up again without asking for confirmation. Relatable.

Claude doing autoresearch on Colab

The whole thing is open source. So if you want to run your own autoresearch experiments — maybe to start writing in Ugaritic cuneiform, or Wingdings — go for it: github.com/JLansey/EgyptGPT


Here are a couple more good ones that might come in handy:

𓐝 𓂝 𓎡 𓃹 𓈖 𓀜 𓄣 𓏤 𓎡
Behold, your heart is tired.


𓊪 𓏏 𓂋 𓊪 𓂝 𓄂 𓂝 𓅓 𓂋 𓊹 𓍛 𓌸 𓂋 𓂋 𓂋 𓎟 𓆑 𓇳 𓎟 𓆓 𓏏 𓇿
Hereditary noble and local prince, overseer of priests, one of his Lord's lovers every day forever.

𓊃 𓅭 𓄿 𓏲 𓀸 𓀜 𓏲 𓀀
Be careful!


𓂜 𓈖 𓈙 𓈖 𓃩 𓀜
There is no shame.


𓏏 𓅱 𓏏 𓀚 𓏥 𓆑 𓅓 𓋴 𓎛 𓍃 𓅓 𓅬 𓅪 𓅓 𓂝 𓋴 𓐠 𓄿 𓀁 𓆑 𓅓 𓂝 𓂝 𓈖 𓀀
His officers were in trouble, his worshippers were in my hand.


For more - head to GlyphGPT