hypermedia production and generative ASCII art

Rochester, NY
Joined May 2015
best agentic sound design 2027
warning: do not turn on your sound Etretat tiles converge: palette-index nGPT mosaic as a 3D ASCIInGPT tumble
1
83
anyone who has ever made a knife can tell you exactly when a knife shouldn't be used as a flat head screwdriver.
53
warning: do not turn on your sound Etretat tiles converge: palette-index nGPT mosaic as a 3D ASCIInGPT tumble
1
3
331
ASCIInGPT dance, beat-tracked to the take you liked
7
327
Etretat tiles, palette-index nGPT (first attempt): mosaic no sound
3
204
Matthew(マシュー)🥭Hendricks retweeted
1/10 🔮 Can a world model learn to make its own future more predictable?* In Latent-Foresight, we jointly learn a compact latent representation of visual foundation model (VFM) features and a generative dynamics model that predicts their future. Here's how 👇
5
28
2
185
11,781
Matthew(マシュー)🥭Hendricks retweeted
are we for fucking real right now 😭
26
44
9
956
100,229
asciinGPT — a world of other things: omnimodal competition
1
5
190
asciinGPT kinetic study 02 — heat and shortest paths
1
1
276
Matthew(マシュー)🥭Hendricks retweeted
"did you read the new @ThinkWiselyMatt post?" "no, did you?" "no"
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more
1
3
1
3
192
Matthew(マシュー)🥭Hendricks retweeted
Uploaded the camera-ready version of our #NeurIPS2026 paper: "Generalized Wasserstein Flow Matching: Nested Couplings for Point Cloud Generation" → Multisample Flow Matching in Wasserstein space 📄 arxiv.org/abs/2605.08424 with R. Duong & G.Steidl :)
1
11
1
78
4,794
this is not what you want the output to look and sound like but it's evidence of progress. Ten nGPTs learn ten forms (grid)
48