open source @roboflow | AI engineering at @UdeSA🇦🇷 prev founder @SatsOnFire

I’m thrilled to present the KAN Convolutional Layer, a promising neural architecture for image processing. Last week KANs came out, as an alternative to the MLP. We extended this idea to Convolutional Layers, creating the KAN Convolution. Join me in this thread to more about it🧵
32
145
1,182
202,937
Alex Bodner retweeted
Messi asked ChatGPT to teach him a chess opening that matched his style. It suggested Goat Horns 🤘
230
318
4,938
743,113
At @roboflow ‘s Visual Intelligence Summit today!
1
1
12
362
Tremendo recibimiento a la banda de Puentes en @Replit
1
12
526
3er día de puentes con esta vistaza
8
194
Mi chofer de hoy: un robot
1
5
370
Alex Bodner retweeted
Puentes starts in two days! If you want to meet any fellows, request intros here: puentes.antigravity.capital/…
Puentes starts this Sunday. We're flying 15 of the best young engineers from Latin America to SF. They’re among the most talented in their countries, and they want to be here to compete with the best. Our goal at @antigravitysf is to help them stay. Meet the engineers 👇
2
4
30
1,191
Welcome to 2026
1
263
How do we do to track an object accurately with a camera moving? Meet Camera Motion Compensation! In practice, you can use BoT-SORT in trackers with a 1 line change: github.com/roboflow/trackers
Object tracking explained in 3Blue1Brown style. Learn about the tracking loop, kalman filters, why occlusion breaks and one way to fix it. Try it out github.com/roboflow/trackers
2
15
94
3,403
Alex Bodner retweeted
Gemini 4 Argon stream in 30 minutes. see you!
Gemini 4 Argon vs GPT-6 Astra YouTube stream tomorrow, Oct 15th, 8 AM PT / 11 AM ET / 5 PM CET save the time and see you tomorrow - detection - segmentation - transcription - data extraction - efficiency and cost what else? link: piped.video/live/bBX_c5AFuMQ
2
1
34
4,342
Alex Bodner retweeted
The fellows want to meet engineers at: @SierraPlatform @posthog @chaidiscovery @linear @WisprFlow @AnthropicAI @OpenAI Instinct @SpaceXSI @modal @PrimeIntellect @ssi @theworldlabs @beltichq If you work or know anyone there, dm for dinner invite :)
Puentes starts this Sunday. We're flying 15 of the best young engineers from Latin America to SF. They’re among the most talented in their countries, and they want to be here to compete with the best. Our goal at @antigravitysf is to help them stay. Meet the engineers 👇
9
43
1,851
Alex Bodner retweeted
Puentes starts this Sunday. We're flying 15 of the best young engineers from Latin America to SF. They’re among the most talented in their countries, and they want to be here to compete with the best. Our goal at @antigravitysf is to help them stay. Meet the engineers 👇
32
71
263
25,098
Muy contento de participar en esta edición de Puentes! Voy a estar viajando el viernes para SF, y buscando conocer gente del ecosistema. Si trabajas en AI, vision, robotica, NLP escribime!
Replying to @GadiBorovich
@AlexBodner_ (22, Argentina). At 16, he co-founded Satellites On Fire and built its wildfire models and alerts (900 monthly users). He now builds Roboflow’s object tracking library (380K+ downloads, 3.9K+ stars) and is first author of Convolutional KANs (170+ citations).
4
2
33
1,019
My favourite thing about @roboflow Trackers is how easy we made it to swap things and create the best tracker for your case. Swap the tracker, the IoU variant, camera motion compensation, dynamic frame rate or masks, one line change, and see what works best! Any detector works.
10
12
130
5,598
I'm still working on the AutoTracking dataset creation. Now I've tried GPT-6.1 Sol on decisions a human would need to make. Astra was good but expensive. At 1/4 of the cost, Sol performs about the same. Stay tuned
We are trying to give a model three words and get back a labelled tracking dataset. No human labels anywhere. After a week, its still not perfect, but the self improvement is working. Out of Astra + SAM3 we can generate some tracks that fragment, but we can use that for training cheaper models that allow us to detect players better and join tracks. Numbers so far: On SoccerNet's official test split, 46 clips it never saw: 62.5 HOTA. For reference on the same clips, published baselines that use SoccerNet's labelled train split or pedestrian datasets: - DeepSORT 36.7 - ByteTrack 47.2 - FairMOT fine-tuned on SoccerNet 57.9 We use none of those labels. Still far behind the 2023 challenge winner at 75.6. Excited for next week progress👀 For which use case would you use this?
2
3
45
2,906
Alex Bodner retweeted
We’re running a personal agents hackathon the last day of Puentes! > Only 50 engineers > $2K in cash for the top 3 teams > Judges like @montonenico, @iAligator, @rincidium > Compete against all the Puentes fellows in SF Link below. @ Saturday, Oct 25
1
17
44
1,397
OpenAI just posted a paper claiming to prove the quasi-Riemann hypothesis: no zero of the Riemann zeta function, or of any Dirichlet L-function, has real part above 11/12. A companion paper pushes it to 7/8. Since Riemann's 1859 paper, nobody had proven any fixed bound like this. If it holds up, it also rules out Siegel zeros. What this means: The zeta function encodes how the prime numbers are distributed. Its inputs are complex numbers, so each zero has a real part and an imaginary part. There are some trivial zeros, we dont care about them. Every other zero is known to have real part between 0 and 1. The Riemann Hypothesis says they should all have real part exactly 1/2. Nobody has proven that. The best known bounds got closer and closer to 1 as the imaginary part grew. That weaker statement is the quasi-Riemann hypothesis, and it's what this paper claims. Siegel zeros are hypothetical zeros extremely close to 1 that have haunted number theory for nearly a century. This result would rule them out. Its still under experts review, but its huge!
We’re releasing a broad range of new mathematical results produced by an internal frontier model. We’ve been consulting with the independent Advisory Group on Mathematics and Artificial Intelligence at the Institute for Advanced Study, and we have drawn on their advice and public recommendations to inform how we release these results. github.com/openai/math
1
7
599
Object tracking explained in 3Blue1Brown style. Learn about the tracking loop, kalman filters, why occlusion breaks and one way to fix it. Try it out github.com/roboflow/trackers
10
137
2,178
129,988
AI could never
I am not joking when I say this. Spotify, Apple Music, and streaming in general is over. AI music is now very, very good. You just don't know yet because all AI music circulating today is from ~2-3 generations ago. Suno v6 pro et al has solved infinite personalized music.
3
519