Maciej Gryka
@maciej.gryka.net
Software generalist with a particular interest in ML and AI. Soft spot for #ElixirLang and #Python. I enjoy challenges of early-stage startups. Ex-CTO, founded a couple companies, PhD in computer vision.
More at https://maciej.gryka.net/
More at https://maciej.gryka.net/
We recently ran a project to help Knowunity cut their LLM bill by half. It’s pretty cool to beat a frontier LLM (Gemini) on all dimensions, which matter: cost, speed, and accuracy by trading off generalization, which is unnecessary here.
More details www.distillabs.ai/blog/how-kno...
More details www.distillabs.ai/blog/how-kno...
How Knowunity used distil labs to cut their LLM bill by 50%
We show how Knowunity use the distil labs platform to fine-tune and deploy their own models, significantly reducing their LLM costs.
www.distillabs.ai
February 9, 2026 at 7:52 PM
We recently ran a project to help Knowunity cut their LLM bill by half. It’s pretty cool to beat a frontier LLM (Gemini) on all dimensions, which matter: cost, speed, and accuracy by trading off generalization, which is unnecessary here.
More details www.distillabs.ai/blog/how-kno...
More details www.distillabs.ai/blog/how-kno...
my coding agent just got confused by cron and timezones, i don’t need any more proof it’s sentient
February 7, 2026 at 6:13 PM
my coding agent just got confused by cron and timezones, i don’t need any more proof it’s sentient
Elixir's operational simplicity (having e.g. a single repo & piece of infra, compared to more moving parts in other stacks) might either be a very big advantage or not matter at all in the new coding-agent world.
I'm like 75% on the side of it turning out to be important, but who knows!
I'm like 75% on the side of it turning out to be important, but who knows!
February 6, 2026 at 1:09 PM
Elixir's operational simplicity (having e.g. a single repo & piece of infra, compared to more moving parts in other stacks) might either be a very big advantage or not matter at all in the new coding-agent world.
I'm like 75% on the side of it turning out to be important, but who knows!
I'm like 75% on the side of it turning out to be important, but who knows!
I love having my biases validated dashbit.co/blog/why-eli...
Why Elixir is the best language for AI - Dashbit Blog
A recent study by Tencent showed that Elixir had the highest completion rate across models when compared among 20 different programming languages. In this article, we explore the reasons why that may ...
dashbit.co
February 5, 2026 at 4:45 PM
I love having my biases validated dashbit.co/blog/why-eli...
those H100s really are nice, huh
February 5, 2026 at 2:20 PM
those H100s really are nice, huh
Reposted by Maciej Gryka
📢 I am hiring a highly-motivated Ph.D student at the University of Copenhagen to work on tokenization-free NLP.
Read our previous work in this topic: aclanthology.org/2025.emnlp-m...
aclanthology.org/2023.emnlp-m...
openreview.net/forum?id=FkS...
Apply by March 8: employment.ku.dk/phd/?show=1563
Read our previous work in this topic: aclanthology.org/2025.emnlp-m...
aclanthology.org/2023.emnlp-m...
openreview.net/forum?id=FkS...
Apply by March 8: employment.ku.dk/phd/?show=1563
February 4, 2026 at 10:40 AM
📢 I am hiring a highly-motivated Ph.D student at the University of Copenhagen to work on tokenization-free NLP.
Read our previous work in this topic: aclanthology.org/2025.emnlp-m...
aclanthology.org/2023.emnlp-m...
openreview.net/forum?id=FkS...
Apply by March 8: employment.ku.dk/phd/?show=1563
Read our previous work in this topic: aclanthology.org/2025.emnlp-m...
aclanthology.org/2023.emnlp-m...
openreview.net/forum?id=FkS...
Apply by March 8: employment.ku.dk/phd/?show=1563
Fun demo we shipped this week: AI slop detector running locally in a browser extension! github.com/distil-labs/...
The utility of the tool itself is questionable :) But it was super fun to build! I was hoping to get something working in a browser for a while, and this shows how :)
The utility of the tool itself is questionable :) But it was super fun to build! I was hoping to get something working in a browser for a while, and this shows how :)
GitHub - distil-labs/distil-ai-slop-detector: Detect AI-generated text locally in your browser
Detect AI-generated text locally in your browser. Contribute to distil-labs/distil-ai-slop-detector development by creating an account on GitHub.
github.com
February 4, 2026 at 5:11 PM
Fun demo we shipped this week: AI slop detector running locally in a browser extension! github.com/distil-labs/...
The utility of the tool itself is questionable :) But it was super fun to build! I was hoping to get something working in a browser for a while, and this shows how :)
The utility of the tool itself is questionable :) But it was super fun to build! I was hoping to get something working in a browser for a while, and this shows how :)
> It would be satisfying if humanity’s ambassadors to distant galaxies turn out to be humanoid robots made by a corporate successor to Twitter Inc.
For the love of everything that’s good @matt-levine.bsky.social
For the love of everything that’s good @matt-levine.bsky.social
February 2, 2026 at 9:35 PM
> It would be satisfying if humanity’s ambassadors to distant galaxies turn out to be humanoid robots made by a corporate successor to Twitter Inc.
For the love of everything that’s good @matt-levine.bsky.social
For the love of everything that’s good @matt-levine.bsky.social
Reposted by Maciej Gryka
And here you go! Definitely doesn't fix the entire state of LLM protocols... yet. But we're on our way. bsky.app/profile/apen...
Coding agents crossed a line this year: they’re useful enough that people are going to use them at work, whether the tooling is ready or not. So... here's some tooling!
tailscale.com/blog/apertur...
tailscale.com/blog/apertur...
Aperture by Tailscale, an AI usage and access tool, now in alpha
Aperture is an AI gateway that doesn't get in the way of developers, and works with most AI tools.
tailscale.com
January 27, 2026 at 4:12 PM
And here you go! Definitely doesn't fix the entire state of LLM protocols... yet. But we're on our way. bsky.app/profile/apen...
tailscale figuring out how to make something sensible out of the current state of all the llm apis wen
I have looked at the actual byte streams LLMs use to communicate with clients and GOOD LORD WHAT THE HECK that is not how any of these protocols are supposed to be used
January 26, 2026 at 2:56 PM
tailscale figuring out how to make something sensible out of the current state of all the llm apis wen
We released a Claude Skill allowing you to very easily get distilled small models, which can run locally on you machine! More here www.distillabs.ai/blog/train-y... and if we give you free training credits when you sign up :)
Train your SLM with distill-cli Claude Skill
Train a custom Text2SQL model by chatting with Claude and the Distil Labs skill. no ML expertise, no data labeling, just a conversation and a few examples.
www.distillabs.ai
January 21, 2026 at 10:42 AM
We released a Claude Skill allowing you to very easily get distilled small models, which can run locally on you machine! More here www.distillabs.ai/blog/train-y... and if we give you free training credits when you sign up :)
I enjoy trying to cram magical Claude words into actual sentences "what do you ultrathink about this?"
January 14, 2026 at 9:22 AM
I enjoy trying to cram magical Claude words into actual sentences "what do you ultrathink about this?"
Playing with @fly.io 's sprites by creating Claude skills to set up sprites for LiveView development. Adding Tidewave was super easy, I guess I should try LiveDebugger next. Many disposable Phoenix apps, here we come!
January 12, 2026 at 9:50 PM
Playing with @fly.io 's sprites by creating Claude skills to set up sprites for LiveView development. Adding Tidewave was super easy, I guess I should try LiveDebugger next. Many disposable Phoenix apps, here we come!
asking Claude Code to run Igniter to install Tidewave to use Claude Code feels Ouroborosy #ElixirLang
December 27, 2025 at 1:08 PM
asking Claude Code to run Igniter to install Tidewave to use Claude Code feels Ouroborosy #ElixirLang
If you're looking into fine-tuning Small Language Models, we've benchmarked a bunch of them to see which perform best. www.distillabs.ai/blog/we-benc...
TL;DR The Qwen3 family is the best all-rounder, while small Llamas show the biggest improvements after fine-tuning.
TL;DR The Qwen3 family is the best all-rounder, while small Llamas show the biggest improvements after fine-tuning.
December 9, 2025 at 4:43 PM
If you're looking into fine-tuning Small Language Models, we've benchmarked a bunch of them to see which perform best. www.distillabs.ai/blog/we-benc...
TL;DR The Qwen3 family is the best all-rounder, while small Llamas show the biggest improvements after fine-tuning.
TL;DR The Qwen3 family is the best all-rounder, while small Llamas show the biggest improvements after fine-tuning.
we just released small-and-mighty distilled PII reduction models, check them out github.com/distil-labs/...
you can run them locally (1B!) and they work as well as much bigger generic models; SLMs FTW!
you can run them locally (1B!) and they work as well as much bigger generic models; SLMs FTW!
GitHub - distil-labs/Distil-PII
Contribute to distil-labs/Distil-PII development by creating an account on GitHub.
github.com
October 16, 2025 at 3:29 PM
we just released small-and-mighty distilled PII reduction models, check them out github.com/distil-labs/...
you can run them locally (1B!) and they work as well as much bigger generic models; SLMs FTW!
you can run them locally (1B!) and they work as well as much bigger generic models; SLMs FTW!
I'll give a demo at the Berlin Elixir Meetup tonight! www.meetup.com/elixir-berli... (last minute change)
Come say hi if Elixir and/or AI is your jam. I'll show how to use distillation (featuring distil labs ofc) to make exmeralda.chat run on a smaller model.
#myelixirstatus
Come say hi if Elixir and/or AI is your jam. I'll show how to use distillation (featuring distil labs ofc) to make exmeralda.chat run on a smaller model.
#myelixirstatus
October 9, 2025 at 10:26 AM
I'll give a demo at the Berlin Elixir Meetup tonight! www.meetup.com/elixir-berli... (last minute change)
Come say hi if Elixir and/or AI is your jam. I'll show how to use distillation (featuring distil labs ofc) to make exmeralda.chat run on a smaller model.
#myelixirstatus
Come say hi if Elixir and/or AI is your jam. I'll show how to use distillation (featuring distil labs ofc) to make exmeralda.chat run on a smaller model.
#myelixirstatus
Over the last couple of weeks we've been working on adding tool calling support to our distillation pipelines. Now you can use it!
As a fun demo, we trained a model to help you remember git commands and it's only 3B so you can run it locally!
www.distillabs.ai/blog/gitara-...
As a fun demo, we trained a model to help you remember git commands and it's only 3B so you can run it locally!
www.distillabs.ai/blog/gitara-...
Gitara: How we trained a 3B Function-Calling Git Agent for Local Use
How we created a local tool-calling language model to turn plain-English language questions into git commands with the accuracy of a cloud LLM. You can check it out in our GitHub repo or get the model...
www.distillabs.ai
October 1, 2025 at 3:07 PM
Over the last couple of weeks we've been working on adding tool calling support to our distillation pipelines. Now you can use it!
As a fun demo, we trained a model to help you remember git commands and it's only 3B so you can run it locally!
www.distillabs.ai/blog/gitara-...
As a fun demo, we trained a model to help you remember git commands and it's only 3B so you can run it locally!
www.distillabs.ai/blog/gitara-...
If you're skeptical of Big AI and want to learn more about Small AI, check out the blog post our CTO, Jacek, just published. Goes through how we can help you turn your big, expensive, small models into beautiful, small, efficient ones www.distillabs.ai/blog/small-e...
Distil Labs
www.distillabs.ai
September 16, 2025 at 6:50 AM
If you're skeptical of Big AI and want to learn more about Small AI, check out the blog post our CTO, Jacek, just published. Goes through how we can help you turn your big, expensive, small models into beautiful, small, efficient ones www.distillabs.ai/blog/small-e...
Reposted by Maciej Gryka
In September, we are hosting Elixir Berlin as part of the #globalelixirmeetups. Join us and other Elixir developers around the globe to celebrate this week!
📅 Hope to see you there! 💜
#ElixirLang
www.meetup.com/elixir-berli...
📅 Hope to see you there! 💜
#ElixirLang
www.meetup.com/elixir-berli...
Sep 25th, [In-Person] Elixir Meetup #112 - Global Elixir Meetup Edition, Thu, Sep 25, 2025, 7:00 PM | Meetup
👋 Hallo und 💜-lich Willkommen to the Elixir Berlin Meetup.
This month we are joining Global Elixir Meetups!
We will have three talks scheduled at a new first time locat
www.meetup.com
September 5, 2025 at 7:40 AM
In September, we are hosting Elixir Berlin as part of the #globalelixirmeetups. Join us and other Elixir developers around the globe to celebrate this week!
📅 Hope to see you there! 💜
#ElixirLang
www.meetup.com/elixir-berli...
📅 Hope to see you there! 💜
#ElixirLang
www.meetup.com/elixir-berli...
Reposted by Maciej Gryka
Phoenix.new by @fly.io is an interesting new entrant into the prompt-driven app development space - it can spin up a full Elixir/Phoenix real-time web app in a neat browser-based IDE, testing via a headless browser while it writes the code
simonwillison.net/2025/Jun/23/...
simonwillison.net/2025/Jun/23/...
Phoenix.new is Fly’s entry into the prompt-driven app development space
Here’s a fascinating new entrant into the AI-assisted-programming / coding-agents space by Fly.io, introduced on their blog in Phoenix.new – The Remote AI Runtime for Phoenix: describe an app in …
simonwillison.net
June 23, 2025 at 6:45 PM
Phoenix.new by @fly.io is an interesting new entrant into the prompt-driven app development space - it can spin up a full Elixir/Phoenix real-time web app in a neat browser-based IDE, testing via a headless browser while it writes the code
simonwillison.net/2025/Jun/23/...
simonwillison.net/2025/Jun/23/...
Reposted by Maciej Gryka
Oban is probably the greatest library I have ever used, especially with Oban.Pro on top. The value you get for free - or for a very reasonable amount - is mind-blowing.
June 20, 2025 at 2:24 PM
Oban is probably the greatest library I have ever used, especially with Oban.Pro on top. The value you get for free - or for a very reasonable amount - is mind-blowing.
Claude just looooooves monkey-patching all over Python tests even though the rules tell it not to do that.
June 13, 2025 at 1:00 PM
Claude just looooooves monkey-patching all over Python tests even though the rules tell it not to do that.
Has there even been a better/worse timing of two papers published the same day?
May 26th 10am: x.com/xuandongzhao... "Learning to Reason without External Rewards: LLMs can learn complex reasoning without access to ground-truth answers, simply by optimizing their own internal sense of confidence."
May 26th 10am: x.com/xuandongzhao... "Learning to Reason without External Rewards: LLMs can learn complex reasoning without access to ground-truth answers, simply by optimizing their own internal sense of confidence."
x.com
May 27, 2025 at 7:42 PM
Has there even been a better/worse timing of two papers published the same day?
May 26th 10am: x.com/xuandongzhao... "Learning to Reason without External Rewards: LLMs can learn complex reasoning without access to ground-truth answers, simply by optimizing their own internal sense of confidence."
May 26th 10am: x.com/xuandongzhao... "Learning to Reason without External Rewards: LLMs can learn complex reasoning without access to ground-truth answers, simply by optimizing their own internal sense of confidence."
Truly an excellent name. I don’t think I’ve ever encountered a better project name.
April 27, 2025 at 7:47 PM
Truly an excellent name. I don’t think I’ve ever encountered a better project name.