Hacker News: SkalskiP

New comment by SkalskiP in "GPT 5.6 Sol is the best "vision" model OpenAI ever released"

SkalskiP — Mon, 17 Aug 2026 18:07:06 +0000

Take a look here: https://playground.roboflow.com/evals. We have few ~30B.

New comment by SkalskiP in "GPT 5.6 Sol is the best "vision" model OpenAI ever released"

SkalskiP — Mon, 17 Aug 2026 18:05:56 +0000

Really? Gemma4-31B should be better than Qwen3.8-27B? I'm happy to test that.

New comment by SkalskiP in "GPT 5.6 Sol is the best "vision" model OpenAI ever released"

SkalskiP — Mon, 17 Aug 2026 16:05:11 +0000

Hi! I’m the author of this blog. I wrote it 4 weeks ago, and it’s already a bit outdated. Gemini 3.7 Flash came out last week, and considering the price, it’s easily the best vision model right now: https://x.com/skalskip92/status/2088032652301304121?s=20

New comment by SkalskiP in "GPT 5.6 Sol is the best "vision" model OpenAI ever released"

SkalskiP — Mon, 17 Aug 2026 15:59:05 +0000

Hi! I’m the author of this blog.

I’m evaluating these VLMs to figure out which ones are good enough to auto-annotate my data, so I can fine-tune my detector.

I wrote a bit more about this here: https://x.com/skalskip92/status/2080334344061694429?s=20

New comment by SkalskiP in "GPT 5.6 Sol is the best "vision" model OpenAI ever released"

SkalskiP — Mon, 17 Aug 2026 15:54:42 +0000

Hi! I’m the author of this blog. GPT-5.6 is much better at vision than previous GPT versions, but it’s still much weaker than Gemini 3.5 Flash or Gemini 3.7 Flash, which was released last week. One interesting approach is to use Gemini through a tool call.

New comment by SkalskiP in "GPT 5.6 Sol is the best "vision" model OpenAI ever released"

SkalskiP — Mon, 17 Aug 2026 15:51:14 +0000

Hi! I’m the author of this blog and benchmark. You’re right. I’ll fix it in the ground-truth dataset. Thanks for pointing it out.

New comment by SkalskiP in "GPT 5.6 Sol is the best "vision" model OpenAI ever released"

SkalskiP — Mon, 17 Aug 2026 15:48:19 +0000

Hi! I’m the author of this blog. I had the same intuition, but together with the OpenAI team we figured out that the issue was image resolution. GPT-5.6 doesn’t handle large images well.

New comment by SkalskiP in "GPT 5.6 Sol is the best "vision" model OpenAI ever released"

SkalskiP — Mon, 17 Aug 2026 15:44:52 +0000

Hi! I’m the author of this blog. I regularly benchmark new VLM releases. You can check the results for Qwen3.8-Max and Qwen3.8-27B here: https://playground.roboflow.com/evals

New comment by SkalskiP in "GPT 5.6 Sol is the best "vision" model OpenAI ever released"

SkalskiP — Mon, 17 Aug 2026 15:38:26 +0000

Hi, I’m the author of this blog. It depends on how strong of a model you need, but in general, Qwen is easily the best among the Chinese models right now.

Over the last two weeks, Qwen released two new models. Qwen3.8-Max is totally insane, but it’s only available through the Alibaba Cloud API. I wrote a similar blog covering Qwen3.8-Max: [https://blog.roboflow.com/qwen3-8-max/](https://blog.roboflow.com/qwen3-8-max/)

If you’re looking for something you can run locally, Qwen3.8-27B might be a great option. On Friday, I did a quick comparison between Qwen3.8-Max and Qwen3.8-27B: [https://x.com/skalskip92/status/2088411215441621469?s=20](https://x.com/skalskip92/status/2088411215441621469?s=20)

New comment by SkalskiP in "GPT 5.6 Sol is the best "vision" model OpenAI ever released"

SkalskiP — Mon, 17 Aug 2026 15:33:04 +0000

Hi, I’m the author of this blog post. I wrote it about 4 weeks ago, and the VLM world is moving so fast that it’s already kinda outdated. I think Gemini 3.7 Flash might be a better choice now, especially when you factor in the price.

Here’s a comparison of the best low-cost models I put together last week. What’s crazy is that Gemini 3.7 Flash is now 50% off on OpenRouter, and this chart doesn’t even account for that discount. https://x.com/skalskip92/status/2088032652301304121?s=20

New comment by SkalskiP in "Basketball Player Tracking, Team Detection, and Number Recognition with Python"

SkalskiP — Tue, 16 Dec 2025 21:07:18 +0000

code: https://colab.research.google.com/github/roboflow-ai/noteboo...

- player and number detection with RF-DETR

- player tracking with SAM2

- team clustering with SigLIP, UMAP and K-Means

- number recognition with SmolVLM2

- perspective conversion with homography

- player trajectory correction

- shot detection and classification

Basketball Player Tracking, Team Detection, and Number Recognition with Python

SkalskiP — Tue, 16 Dec 2025 21:07:18 +0000

Article URL: https://www.youtube.com/watch?v=yGQb9KkvQ1Q

Comments URL: https://news.ycombinator.com/item?id=46294476

Points: 1

# Comments: 1

New comment by SkalskiP in "[dead]"

SkalskiP — Tue, 03 Sep 2024 13:37:10 +0000

use computer vision to automatically extract player and ball position, plot it on pitch radar, and calculate advanced metrics

New comment by SkalskiP in "Video segmentation with Segment Anything 2 (SAM2)"

SkalskiP — Fri, 02 Aug 2024 08:10:39 +0000

yup! the point here is to show step by step how to perform video segmentation with SAM2

Video segmentation with Segment Anything 2 (SAM2)

SkalskiP — Thu, 01 Aug 2024 22:11:40 +0000

Article URL: https://blog.roboflow.com/sam-2-video-segmentation/

Comments URL: https://news.ycombinator.com/item?id=41134167

Points: 32

# Comments: 3

New comment by SkalskiP in "Supervision: Reusable Computer Vision"

SkalskiP — Mon, 25 Mar 2024 13:52:41 +0000

Hi! Supervision does not run models, but it connects to existing detection and segmentation libraries, allowing you to do more advanced stuff easily. Take a look here to get a high-level overview: https://supervision.roboflow.com/latest/how_to/detect_and_an....

As for Roboflow, you can use the `inference` package to run (among other things) all Roboflow Universe models locally. Take a look at README examples: https://github.com/roboflow/inference.

New comment by SkalskiP in "Supervision: Reusable Computer Vision"

SkalskiP — Mon, 25 Mar 2024 12:06:32 +0000

You can always slice the images into smaller ones, run detection on each tile, and combine results. Supervision has a utility for this - https://supervision.roboflow.com/latest/detection/tools/infe..., but it only works with detections. You can get a much more accurate result this way. Here is some side-by-side comparison: https://github.com/roboflow/supervision/releases/tag/0.14.0.

New comment by SkalskiP in "Supervision: Reusable Computer Vision"

SkalskiP — Mon, 25 Mar 2024 12:03:43 +0000

Hi swyx! The easiest way would be to train a custom model to detect raised hands. I found one on Roboflow - https://universe.roboflow.com/search?q=raised%20hand. I'm not sure how good it would be on your images, so I'd recommend adding some of your pictures. Then you just detect hands and detect people and calculate the ratio.

New comment by SkalskiP in "Supervision: Reusable Computer Vision"

SkalskiP — Mon, 25 Mar 2024 08:47:20 +0000

Oh my, if you'd like to contribute lens distortion removal... That would make me super happy!

I'm 95% sure I'll be in Seattle this year.

New comment by SkalskiP in "Supervision: Reusable Computer Vision"

SkalskiP — Mon, 25 Mar 2024 08:09:14 +0000

Hi everyone! I'm one of the maintainers of Supervision. Thanks for putting our project on the HN front page. It really made my day!