Nice summary of our tech report

We're publishing the technical report for Laguna M.1 and Laguna XS.2 today. It's a bit of an unusual kind of tech report: We talk about two model generations at the same time. In addition to the technical details, we really wanted to share not just what went into them; but also how we approach model building. poolside.ai/assets/laguna/la…

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/la…

I just tried Mapterhorn terrain in OpenGlobus - and my first impression is literally: WOW, it looks amazing! Clean, detailed, visually pleasant relief, and it loads surprisingly fast. Really like the idea behind it: open-data terrain built for modern web mapping. Huge respect to @leichteralsluft for pushing this forward. Check it out 👉 mapterhorn.com/ #OpenGlobus #Mapterhorn #WebGL #GIS #OpenData #3DMaps

Good morning researchers and technical builders in London👋🇬🇧 100 applications in under 24 hours🤯 — only a small share will make it in! We're hand-picking a small group of the strongest researchers to spend a weekend pushing @poolsideai's Laguna XS.2: fine-tuning, RL environments, quantization, inference. Pizza, networking, special guests and the winning team walks out with an @nvidia DGX Spark™ 🤩 Apply here👉luma.com/poolsidehackathon

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-the… Examples below 👇 1/

Go check out our new beautiful eval charts that my friend made 🚀 poolside.ai/blog/laguna-a-de…

Cannot understate how critical and instrumental to our inference story @baseten has been, and great people to work with to top it off!

We are an American company with a global team and global aspirations. The story of @poolsideai is that early on in the life of the company we decided to focus on building out our applied research org. in Europe. That’s been the seed for an amazing team and a competitive advantage. Today we have team members all over the world, Europe and US are roughly equal in size, Asia is growing. Three years ago we thought France would be a great place to build from but in the early days found our hiring happened all across Europe instead. Today we have less than a handful of folks in France but large teams in Europe in London, Amsterdam, Zurich etc. We operate as a remote first company but have an office in Paris where we do monthly on-sites (it is great logistics for this) and an office in London which is used on a daily basis. When we raised capital early on, the vast majority of it came from US investors but European (including French ones) have been a part of our rounds. When we got to France (almost 3 years ago) we were offered significant double digit million research grants. My cofounder @jasoncwarner and I did not feel comfortable accepting the grants when we realized that France was going to be only a small part of our story. So we respectfully turned them down. France keeps a special place in our hearts but we’re a global company with global aspirations.

I have been involved in many model launches at different places, but this one is the first that feels **industrial** Poolside talks a lot about the model factory, and this is not just some marketing point:

This is one of the things I’m most proud of our team for. Our Model Factory approach meant it took <5 weeks from very first step on pretraining to public release.

I'm particularly excited for Laguna XS.2, our open weight model you can run on your own hardware. This thing is smart and fast. Use it for free in our sandbox env shimmer.run with a Next.js app skeleton for maximum fun.

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.

We believe that to compete at the frontier, you have to own the full stack: from dirt to intelligence. Today we’re announcing two major unlocks for our mission to AGI: 1. We're partnering with @CoreWeave and have 40,000 NVIDIA GB300s secured. First capacity comes online starting Dec ’25. 2. Project Horizon: Poolside is developing a vertically integrated 2GW AI campus in West Texas to secure our medium term scale. On this site @CoreWeave will be our anchor tenant for the first 250MW phase. Learn more about it on our blog: poolside.ai/blog/announcing-… Or on WSJ: wsj.com/tech/ai/a-giant-new-…

The tech preview of LLMD is out: - Easy Setup - Just mount your model and run - Cross-Platform GPU Support - Single container works on *both* NVIDIA and AMD GPUs - Lightweight - Only 2.4GB container size - High Performance Enjoy !

We can finally say it publicly: @poolsideai got their models running on @awscloud’s Trainium/Inferentia thanks to @zml_ai. No code change. Promise kept.

H200 go brrrr with @zml_ai's llmd

Come find us next week, lots to show and to talk about :-)