@sarna_dev
Account based inPoland
About this account
- Account based in
- Poland
- Connected via
- Web
Account-level information from X, not a live location or the device used for a specific post.
Pinned Tweet
most important lesson from years of distributed systems: keep everything on a single machine for as long as humanly possible
Piotr Sarna retweeted
Nice blog post on the upcoming Japanese translation of Writing for Developers.
ブログ書きました。僕が監訳した本が9月17日に発売されます！みなさんよろしくお願いします 🙏
「世界で闘う エンジニア・アウトプット力を鍛える本」を監訳しました（2026年9月17日発売） - give IT a try blog.jnito.com/entry/2026/09…
Piotr Sarna retweeted
ブログ書きました。僕が監訳した本が9月17日に発売されます！みなさんよろしくお願いします 🙏
「世界で闘う エンジニア・アウトプット力を鍛える本」を監訳しました（2026年9月17日発売） - give IT a try blog.jnito.com/entry/2026/09…
I don't understand a single word, and yet it's the most satisfying author copy I've received to date.
fyi @bcantrill if you ever need to formally spell your name in Korean!
Meet… Arena Conversations. @petergostev sits down with @poolsideai researchers,Connor Adams and Aalhad Patankar, to discuss how they’re building frontier open coding models.
Episode drops today at 10am PT on our YouTube.
They dig into Poolside's Laguna model family, why the team publishes full trajectories (not just benchmark scores) for anyone to audit, and how "experiments" at Poolside range from data mixes to harness design to reward-tuning decisions run tens of thousands of times a day.
Piotr Sarna retweeted
We started the MLX.fast challenge with @poolsideai with one key question. How much faster can the community make Laguna XS 2.1 run on a Mac?
The answer so far has been 2.6x faster.
Nearly 1,800 submissions and 35 solvers later, the challenge comes to a close today.
And there’s one more thing. One of the solvers is taking home a Mac Mini M4 24GB!
Winner below ↓
Piotr Sarna retweeted
One way to fall behind in data science has nothing to do with models or tools. It's struggling to explain your work.
In Writing for Developers, @c_a_dunlop and @sarna_dev share practical techniques for communicating technical ideas with clarity.
Hear Cynthia on Value Driven Data Science: hubs.la/Q04sj7qG0
Book: hubs.la/Q04sj9Zy0
July in writethat.blog 👇
Tailscale didn’t stop the Hugging Face intrusion // @apenwarr, @Tailscale
Finding bugs in Raft implementations // TW Lim, Rohan Padhye, Marco Primi, @AntithesisHQ
I'm sorry, Dave // @dhh
Watching Go’s new garbage collector move through the heap // @eatonphil, @theconsensusdev
Running unmodified Doom in the SQLite bytecode language // @glcst, @tursodatabase
My thoughts on the Bun Rust rewrite // Andrew Kelley
Performance per dollar is getting faster and cheaper // Ian Ye, @wafer_ai
agent sandboxing techniques by level of isolation:
- bwrap/landlock/seccomp/seatbelt
- userspace kernels/syscall capture
- rootless containers
- virtual machines
- someone else's laptop
Piotr Sarna retweeted
We just crossed 10T tokens served across all our models in less than 3 months!
Laguna S 2.1 is pushing new highs at ~300B tokens a day, and has processed +2T in the 14 days since release.
That’s across @OpenRouter @vercel and our direct API.
Really good to see demand for open models keep accelerating.
💪
We've improved our serving efficiency and increased rate limits by +10x. The update is live on @OpenRouter @vercel AI Gateway and platform.poolside.ai.
Thank you to everyone who has used the model, shared feedback and stuck with us while we improved the experience!
Usage is already climbing. On OpenRouter alone, Laguna S 2.1 is on pace for ~250B tokens today, 4x our daily average this week.
We are also taking 10% off our paid endpoint on OpenRouter. It's a dedicated deployment with the full 1M context window for the best performance on harder tasks.
Run Laguna S 2.1 in pool or Poolside Desktop Assistant, or plug it into @opencode, @NousResearch Hermes Agent, @kilocode, @cline or @pidotdev and let it run over the weekend.
We'll be watching the graphs.
also, loop spelt backward is pool - the universe is giving you a hint to switch to @poolsideai pool for daily agentic workloads
github.com/poolsideai/pool
Piotr Sarna retweeted
Building AI in the open makes the world more secure.
We’re joining the Open Secure AI Alliance to build open tools that safeguard software and agents.
We’ll keep releasing model weights and evaluations and sharing our research to strengthen a broader open ecosystem for defenders.
Excited to contribute alongside @nvidia and the other organizations building this ecosystem.
Attackers have frontier AI. Defenders need a frontier AI ecosystem—the best open and closed models, force-multiplied by a global community.
During the Hugging Face incident, closed AI blocked essential forensics. An open-weight frontier model helped contain the intrusion.
That’s why we created the Open Secure AI Alliance.
Piotr Sarna retweeted
Poolside Desktop Assistant is available today for macOS, VS Code, and Visual Studio.
Download it and put it to work: poolside.ai/downloads/deskto…
Learn more about why we built it: poolside.ai/blog/introducing…
Try it now and tell us what to build next in Discord: discord.gg/NAnCKRbZa
JUST PUT @risc_v LINUX IN YOUR BROWSER RIGHT NOW
The time has come, and rave is mature enough to actually boot a real tiny RISC-V Linux image in your browser. No virtio yet, but UART is just enough to give it a try and lurk around the system with busybox.
rave.sarna.dev
Special thanks to @poolsideai Laguna S for ever-thorough reviews and @buildrootorg for making it so easy to build minimal Linux kernels and initramfs!
🤖 Made with AI
Today we're releasing Laguna S 2.1, our most capable model to date.
It's a 118B total parameter Mixture-of-Experts model with 8B activated per token, a context window of up to 1M tokens, and thinking and no-thinking modes.
Capable enough to hold its own against models many times its size. Small enough to run on a single @NVIDIAAI DGX Spark.
Laguna S 2.1 is fully open under OpenMDW-1.1, with weights available today on @huggingface
poolside.ai/blog/introducing…