Viewing profile — maciejgryka

I’d bet there are as many stories of businesses failing because of inability to ship quickly as there are about focusing too much on your tooling instead of delivering value to cus…

We used our distillation platform & a Kaggle dataset to produce a tiny (270M Gemma base) model to classify text into "AI slop"/not classes. It's fun to play with and was fun to bui…

We used our platform to fine-tune a tiny text-to-SQL model using distillation from DeepSeek V3. Repo has instructions for how to replicate this. This is definitely not the best-per…

We benchmarked which small language models are most tunable and which deliver best performance after fine-tuning. Tested 12 models (Qwen, Llama, Gemma, Granite, SmolLM) on 8 tasks.…

Huh works fine for me, even when not logged in to Github. Can you try again?

We've been experimenting with small models for structured tool calling tasks and just released gitara. Both the 3B and 1B models turn natural language instructions into valid git c…

I think it’s going to be a while before we see small models (defined roughly as “runnable on reasonable consumer hardware”) do a good job at general coding tasks. It’s a very broad…

I think this is a description of how things are today, but not an inherent property of how the models are built. Over the last year or so the trend seems to be moving from “more da…

I’d encourage everyone, who finds this appealing to check out how Ecto works in Elixir. It’s all functional & immutable goodies and pipelines are built into the language and idioma…

Highest-end fidget spinner I’ve ever seen. Instantly appealing to my inner 6-year-old.

Yes, compute is absolutely the limiting factor today. Not only because the space of hyperparameters is huge and having more compute would make it easier/possible to explore. But al…

> “Retrieval-Augmented Generation” is nothing more than a fancy way of saying “including helpful information in your LLM prompt.”

There's hype and FOMO for sure and you're right that there's lots to learn from information retrieval work. But why be dismissive of the whole thing? People learning from past rese…

For sure, it's only worth doing if you actually have so much relevant data that it doesn't fit in the context! This is definitely the case for us for this problem, but it's not uni…

This is one of the things we learned recently about building production workflows with LLMs. Happy to answer any questions/feedback here <3

I have no actual info on this, but I always assumed they'd compute some mutlimodal embeddings of the screenshots to then retrieve semantically-relevant ones by text? And yeah, they…