Grzegorz Szpak

Backend & infra @ @poolsideai
Vibe coding with @sarna_dev

[antirez @antirez]

Now with the upcoming release of the new DS4F checkpoint, and I believe later with Laguna S2.2 or a new S2.1 checkpoint, DwarfStar is going to be better at zero development costs. It is important to invest in the right models that get better and are locally runnable.

[Sudo su @sudoingX]

i have not been this surprised by a model on the dgx spark since stepfun 3.7. and this time it's an open one from an american lab.

i asked @poolsideai's new laguna s 2.1, serving on hermes agent to build me a simple gpu marketplace design. it built scaffolded full multi-file in one shot, a hero section, a live pricing grid, a comparison table, working deploy buttons, the whole thing.

and then it did what i never asked for. it installed its own dependencies, started a dev server, pulled my machine's ip, and served the site on my network so i could open it from another device.

0 back and forth. it planned the multi file structure, wrote every file, wired them together, and shipped a running app, all on a desk box, all from a local open weight model.

this is the line between a model that chats and a model that works, and laguna s 2.1 walked straight across it. i've watched a lot of models on this box, and the ones that make me sit back like this are rare. stepfun 3.7 did it. this just did it again

the gallery is the result. next i'll show you how it built the whole thing in a single shot, start to finish. that part is even better.

[Eiso Kant @eisokant]

Learning we have some bugs on the RTX6000. We’re on it. Team has worked non stop last days and it’s getting late for a lot of the inference folks, so might be until tomorrow till we have a solution.

[Grzegorz Szpak @gszpak2]

David vs Goliath(s) 🫡

[Eiso Kant @eisokant]

Building foundation models is hard work and you are compounding progress with time and effort. @thinkymachines is building their model factory and the model coming out is a moment in time. That’s it. We should be applauding everyone who is joining this race and even more so when they’re choosing to open up their research and their work. Having been in this arena for years now, I have an immense amount of respect for anyone willing to enter it and compete. Congratulations on your release TM! You guys rock. Onwards and upwards 🚀

[Grzegorz Szpak @gszpak2]

Amazing story showing that, given access to the right tools / context, AI agents will be able to solve more than we have ever been able to.

2026 is officially the year of AGI.

https://t.co/Yh0TOeQbqv

[NVIDIA AI @NVIDIAAI]

Some more amazing models launched today!

Congrats to @poolsideai on the release of Laguna XS.2 and Laguna M.1

[almonk @almonk]

shimmer also runs entirely on your phone. An instant-on VM, with Poolside Agent in split screen and a full dev environment - pinch me
https://t.co/ds6LMCx653

[George Grigorev @iamgrigorev]

We just released our first models at @poolsideai – including Laguna XS.2 (open weights) that competes with Qwen3.6-35B.

I worked across pretraining — happy to answer questions! We now have great understanding of exactly all components that went into training through principled ablations, and now we're confident to scale.

This year would be 🔥 for us! More coming very soon

[ollama @ollama]

First open-weight model from @poolsideai! Apache license, and available on Ollama to try.

👇👇👇 model page

[Eiso Kant @eisokant]

Today we’re shipping Laguna M.1 and Laguna XS.2 – our first public models. We’re also shipping our agent harness and a preview product experience.

Both models were trained from scratch on our own stack: data pipelines, training infrastructure, and agent RL.

[Jason Warner @jasoncwarner]

Today @poolsideai is releasing Laguna M.1 & Laguna XS.2, our latest generation models and first public models

We started Poolside because we believed that to build truly capable coding agents, you need to own the full stack: data, training, reinforcement learning, inference.
These models are the first result of that work, and we’re making them available to everyone

[Grzegorz Szpak @gszpak2]

Excited to finally share what we've been building!

[Poolside @poolsideai]

Today we’re releasing Laguna XS.2, Poolside’s first open-weight model.
It’s a 33B total / 3B active MoE model built for agentic coding and long-horizon tasks.
Trained fully in-house on our own stack. Runs on a single GPU. Released under Apache 2.0.
Links 👇
Weights: https://t.co/HSo8L2gM64
API: https://t.co/DMJtNFrace
Blog: https://t.co/BXEjQxtQoV

[Poolside @poolsideai]

Today we’re releasing Laguna XS.2, Poolside’s first open-weight model.
It’s a 33B total / 3B active MoE model built for agentic coding and long-horizon tasks.
Trained fully in-house on our own stack. Runs on a single GPU. Released under Apache 2.0.
Links 👇
Weights: https://t.co/HSo8L2gM64
API: https://t.co/DMJtNFrace
Blog: https://t.co/BXEjQxtQoV

[Grzegorz Szpak @gszpak2]

@AdrianKowollik @Dan_Kostecki Jaki jest problem w refinansowaniu na zmienną stopę w przypadku obniżki RPP i zerowej prowizji od całkowitej spłaty?

[Grzegorz Szpak @gszpak2]

@marcingielzak HoC:)

[Tomasz Jaroszek @TomaszJaroszek]

Najprzyjemniejsza twitterowa tradycja :)

Za każdy tweet lub retweet z hashtagiem #MastercardGrazWOŚP, Mastercard przekaże 5 zł na WOŚP💰💰💰

Wielka prośba o napisanie swojego tweeta z tym hasztagiem albo po prostu podanie dalej tego i lecimy 🚀

[Jacek Migdal @jakozaur]

How it started vs How it's going

Why Poland is frequently forecasted as doomed to fail, yet actual economical performance is impressive.

Screenshot from @TheEconomist 2014 forecast vs. 2023 actuals.

🧵

[Grzegorz Szpak @gszpak2]

@zerohedge @Robert_Kosiorek BS, it doesn’t imply that. Learn statistics.

[Grzegorz Szpak @gszpak2]

@fiat_money I w 90% techów, w Polsce też