creations with code and networks

Joined June 2011
1,507 Photos and videos
pleased to be showing new screenprints at @CVPRConf this weekend. these use mechanistic interpretability techniques to highlight features shared across a wide family of vision models
1
4
17
1,527
Each print's unique backlighting element is provided by a TIPS model. This shows spatial patch level activations highlighting visually where that model attends to when activating its analogous feature.
1
2
446
If you are at CVPR drop by - six pieces are on display today and tomorrow just behind the Google booth in the #CVPR2026 art show. I'll be there for daily artist talks on the official schedule or DM if you'd like to meet up and chat.
1
2
11
1,536
saxophone print top-150 SigLIP image probe though mknn model agreement (a la platonic representation hypothesis) is not part of the test time compute process, it climbs naturally as the as the optimization evolves
2
11
782
the models, they just wanna converge
7
445
unsure how AI interprets this print? treating the image as a linear probe on your favorite vision model and scraping a diverse dataset for maximum activations provides a coherent suggestion.
1
2
10
1,528
"pirate ship" (ImageNet class 724)
1
4
450
45% mutual kNN between CLIP and SigLIP — not bad for two model families trained on different data with different objectives when probed with this print. revisiting ImageNet so I can build a toolbox for navigating more uncharted waters without class labels (stay tuned)...
6
292
traffic sign, baseball player, pomegranate
2
1
16
910
not seeing it? don't worry - your favorite imagenet model is.
1
7
678
or query your favorite vision model for semantic nearest neighbors - here's OpenAI-CLIP's top hits across CC3M using the baseball_player print as a probe
2
228
piggy bank (ImageNet class 719)
1
2
358
Weapons-grade piggy bankness: One drawing. No training. Subtract the style, get a direction in SigLIP space. Sort 50K ImageNet images by cosine similarity: 41 of the top 50 are piggy banks (P@50 = 82%). The drawing is the classifier.
1
1,270
18 Nov 2025
see the skull?
2
8
835
18 Nov 2025
a hard "yes" from Gemini 3 ✔️
4
635
4 Nov 2025
do you see the power? @grok
2
2
4
718
4 Nov 2025

4 Nov 2025
Replying to @dribnet
Yes, I see it—the raw energy in those symmetric blue and yellow strokes, like twin beasts facing off. Clever perception play! What's the story behind this one?
1
681
29 Oct 2025
. @grok? 👇
29 Oct 2025
do you see the creature?
2
3
1,033
29 Oct 2025

29 Oct 2025
Replying to @dribnet
Yes, I see it—a symmetrical blue inkblot forming a fierce creature's face, with orange lines highlighting angry eyes, a triangular nose, and a downturned mouth. Looks like a spiky-maned monster or lion staring intensely. Neat creation!
2
649