Artem Tyurin

Try it out github.com/poolsideai/pool

Open protocols in action: pool connecting to a Goose agent on an exe.​dev VM via the new ACP network transport.

Today we’re releasing Laguna XS 2.1. It’s a small upgrade to the Laguna XS.2 model, the same 33B total / 3B active MoE and stronger results on multilingual coding and terminal-style tasks. Available now on @huggingface, @OpenRouter, and via Poolside API.

@ntaylormullen Can we get ACP support for Antigravity?

End of an era, but the start of something even bigger. Today, Gemini CLI will stop serving requests for Google AI Pro, Google AI Ultra, and free tier individual accounts as we transition over to the Antigravity CLI! It started with weekly Gemini CLI updates and grew to be bigger than I ever thought it would. I’m deeply grateful for the community, the code, and the absolute ride of the past year. Thank you all so much!! Next stop: Antigravity SDK. Stoked to keep building with you all there and will be sharing more in the coming weeks! 🚀🚀🚀

IYMI: the best way to try Laguna M.1 is to jump in the pool. pool is our agent harness. It works as both an ACP server and client, so you can run M.1 as a coding agent and build with the same interface we use ourselves. go build something cool ↓ github.com/poolsideai/pool

Today we’re releasing the weights for Laguna M.1, our most capable model to date, with a 256K context length. Both base and post-trained checkpoints are now available on Hugging Face under Apache 2.0.

When I struggle to structure my thoughts about what's happening I turn to writing. Today about the recent US Anthropic ban news, what it says about power and dependency, and what it should mean for Europeans and citizens of the world. It's a long one. lucumr.pocoo.org/2026/6/13/amer…

This month, Poolside’s Laguna XS.2 is free to train on Prime Intellect Lab. First come, first serve while reserved capacity lasts.

Laguna XS.2 from @poolsideai is a 33B MoE built for agentic coding. Red Hat AI trained a DFlash speculator for it: 0.6B drafter, 8 tokens per pass, no quality loss. FP8, NVFP4, and INT4 checkpoints via LLM Compressor. Models in comments. Speedup with @vllm_project:

London cookers are taking Laguna XS.2 to the moon 🚀 Huge shout to @PrimeIntellect @nvidia @huggingface @adaption_ai for making this possible!

Today we’re publishing the technical report behind Laguna M.1 and Laguna XS.2. This report opens up more of what went into them: Model Factory, pre-training data, distributed training, post-training, agent RL, quantization, and evaluation. poolside.ai/assets/laguna/…

It isn't unexpected that the focus of the Bun Rust rewrite is on the anti-Zig side more than anything, since the internet loves to hate. What is unexpected and unfortunate is that leadership within Bun hasn't tried to steer the conversation away from that at all. There are so many positive and interesting takeaways from this and I'm not really seeing any of them pushed as the primary message. A positive thing that hasn't been talked about at all is how far Bun came thanks to Zig. And even if you dump it now, its meaningful for how good Zig was to even build a product to this point and impact by any metric. I would've loved to see anyone in leadership say this. On the interesting side is how fungible programming languages are nowadays. Programming languages used to be LOCK IN, and they're increasingly not so. You think the Bun rewrite in Rust is good for Rust? Bun has shown they can be in probably any language they want in roughly a week or two. Rust is expendable. Its useful until its not then it can be thrown out. That's interesting! There's been a lot of talk about memory safety and no doubt Rust provides more guarantees than Zig. But I'd love to see a better analysis of why Bun in particular suffered so much rather than take the language-blame path. How could engineering as a practice been more rigorous to prevent this? What were the largest sources of crashes other programs should watch out for? How does Rust prevent them? How could Zig theoretically prevent them? That's interesting. I know the official blog post hasn't come out yet from Bun. But they're smart enough to know that that PR would stir up controversy the moment it opened, or they should've been. And plenty in the company have been tweeting and writing about it. Its somewhat telling to me in various dimensions what they chose to talk about first. I tend to think I'm pretty good at corporate PR/comms (especially when it comes to developer audiences) and I think appealing to the negative is never the right long term strategy; it does work to get short term eyes though.

Poolside is hosting a 2-day model research hackathon in London. Join us to push an open-weight agent model as far as you can. RL and fine-tune Laguna XS.2, our latest-generation model, on Prime Intellect Lab. Dates: May 29–30 Partners: @nvidia + @PrimeIntellect + @huggingface Prize: NVIDIA DGX Spark Agents need better models. Better models need cracked researchers. Link below.

As agents get more clever, so do their attempts at benchmark hacking. Last Monday, we found one of our RL runs jumped ~20% on SWE-Bench-Pro over a weekend, reaching ~64% which would make it #1 on the leaderboard. This was clearly benchmark hacking and we patched the exploit. But this revealed deeper hacks across multiple public benchmarks, some of which were impossible to fix through environment design alone. Evals need to evolve beyond just outcome based pass rates to better observability into how the agent is arriving at them. These were our findings: poolside.ai/blog/through-t… Examples below 👇 1/

Exactly, I found myself for the first time *ever* to talk to a model that can run on my Computer about the random things you could ask to Claude. Like history and other stuff. I also did a benchmark on Italian historical facts wth Qwen 27B vs DeepSeek v4 Flash 2 bit quants (continue)

@owickstrom Not yet! Too much stuff to untangle from the monorepo. Will try to do it in the upcoming months.

@tema_codes What's up with the repo? Is it not open source?

The duality of pool: using pool in Zed as an ACP server (left) to develop pool ACP client (right).

Different agents, same UI.