I'm happy to share that a new version of OSCAR is here! 👯♂️
OSCAR 23.01 is full of cool new features 👀.
It has been created using our trusty #rustlang pipeline, ungoliant, on which we have been hacking new stuff in lsat year.
Spoiler alert: ungoliant is faster than ever! 🚴🏼💨
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.
https://t.co/RWk2F9IrAI
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.
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.
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
Training AI models requires storing temporary data mid-process. That data sits in GPU memory taking up space until it's needed. The standard fix has always been to delete it and redo the work later. It works, but it's wasteful.
If you want to help us improve language and cultural coverage, and build an open source LangID system, please register to our shared task! 💬
Registering is easy! All the details are on the shared task webpage: https://t.co/bJs8uY39wo
Deadline: July 23, 2025 (AoE) ⏰
#WorldMentalHealthDay: Today is an opportunity to discuss what more needs to be done to make mental health care a reality. Safe, healthy working environments can act as a protective factor for mental health. Let's take action today for a healthier future. https://t.co/asg6TlT6qG
Hey folks, we're soon going to open @zml_ai to design partners and alpha testers. If you're interested, let me know.
In the mean time, here is a quick demo we did a while ago of the EnCodec AI Audio Codec built right in the @FFmpeg binary using our tech.
Video link next 👇
👋🤩 @AirbudsWidget is hiring! Join us as a full-time @golang Backend Developer.
Work with a passionate team of five, build features users love, and make an impact in the music social app space. Works in Paris timezone.
Apply now: https://t.co/mWZcuFGMF2
Announcing mOSCAR, multilingual interleaved text-image corpus as part of @oscarnlp project.
Paper: https://t.co/1hhnyYCyI3
Dataset: https://t.co/hiEUJ1Q3iJ
Doc: https://t.co/KsnT5wVee2
1/6