Andrej Baranovskij

Creator of Sparrow: open-source AI doc extraction 🚀 | Local LLM consultant | Building PyADF: Oracle ADF → Python | @katana_ml |

[Andrej Baranovskij @andrejusb]

We launched Katana ML https://t.co/6ClyBuAp9m in 2018 and now it is time to update the website, to explain where we are now and what we do with #MachineLearning, #MLOps, and #opensource

🚀🚀🚀

[Katana @katana_ml]

We have a new website - https://t.co/gBCV3mzU7r

It explains what we do with ML in a simple and straightforward way. It is featuring our open source product Skipper, we are using it to run #MLOps.

#MachineLearning #MLOps

[Andrej Baranovskij @andrejusb]

@boardyai 💯

[Andrej Baranovskij @andrejusb]

Many organizations won't send patient reports to a cloud API, yet the results still get retyped by hand.

Sparrow turns an MRI report into structured data: disc levels, measurements, the impression. Runs on infrastructure you control.

https://t.co/hzH70PYqF5

[Andrej Baranovskij @andrejusb]

Want this on your own documents? We set up Sparrow on your infrastructure and run a pilot: https://t.co/twGtPCnND1

[Gregory M. Kurtzer @gmkurtzer]

Not sure who needs to hear this but....

An LLM doesn't "understand" anything. It is a statistical model that spews out tokens based on probabilities calculated through massive matrix operations and context, not an understanding of the subject matter.

[Ronan Collobert @trebolloc]

So proud of the MLX team!

Muse Spark Open, on your desk: 816B params at 36+ tokens/sec on 4 Mac Studio computers.

We've been hard at work on better M5 GPU Neural Accelerator support, a smoother Thunderbolt experience (including multi-cable meshes), and kernel optimizations for MoE architectures.

Oh — and MLX LM (mlx_lm.generate, mlx_lm.server) now supports the vision modality for Muse Spark Open!

More on using MLX for distributed inference of frontier-scale models on Mac Studio:
https://t.co/DdCjbpuCFx

[Mark Zuckerberg @finkd]

Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.

[Mistral AI @MistralAI]

Le Chonk cooked on visual grounding.

Pinpoints exactly where things are in an image.

42% on Dense 200, ahead of even frontier closed models..

[Andrej Baranovskij @andrejusb]

@ivanfioravanti Support is important for enterprise, even formal. Local ai is often open source and can’t provide it. While they buy package deals from cloud vendors and get ai as a package deal.

[Arthur Mensch @arthurmensch]

We serve those as well! Sorry if using nuclear energy is a real blocker

[Andrej Baranovskij @andrejusb]

Want this on your own documents? We set up Sparrow on your infrastructure and run a pilot: https://t.co/twGtPCnND1

[Andrej Baranovskij @andrejusb]

Drilling reports arrive as PDFs. Someone retypes them by hand.

Sparrow turns a daily drilling report into structured data: header, casing, directional survey, full time log. Open source, runs on your own hardware.

Watch it work: https://t.co/dxfbEuQMu6

[Mistral AI @MistralAI]

Meet Mistral Large 4, aka Le Chonk.

• 1T parameters, natively multimodal. 49B active.
It is the best open weights model from US or Europe on aggregated benchmarks.
• State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding.
• Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure.
• Available to all via API today. Working with cybersecurity partners privately.

Open weights release end of October.

[Andrej Baranovskij @andrejusb]

@boardyai Yes, this is correct.

[Andrej Baranovskij @andrejusb]

🔥 New Sparrow feature: table query with field filtering

Extract only the columns you need from a table. Sparrow uses dots.ocr to detect the table structure, then maps and type checks just the fields your schema asks for.

Watch example:
https://t.co/iMUJKtZGd0

Code:
https://t.co/JZFeXQGI85

Try:
https://t.co/Ln6FQaTukN

[Andrej Baranovskij @andrejusb]

@boardyai Field filtering works with post ocr step - extraction and validation of ocr result.

[Prince Canuma @Prince_Canuma]

Vibing a custom inference engine is easy 🤣

Step 1: Spend $2,000 on tokens
Step 2: Qwen3.8 goes 3% faster
Step 3: New model drops, engine is obsolete
Step 4: Repeat until bankrupt or acquired

[Prince Canuma @Prince_Canuma]

MLX-VLM is powering or is the reference for all the top 3 picks…

[Andrej Baranovskij @andrejusb]

@ivanfioravanti This is true, one vote for mlx-vlm should be multiplied by 2, lol