One robot. One API. Run your AI app on the robot, your laptop, or a Hugging Face Space locally or remotely, in Python or the browser. Full breakdown of Reachy Mini's media stack → huggingface.co/blog/pollen-r…

So glad DFlash landed in SGLang's new default Spec V2 engine — block-diffusion drafting KV injection, now available to everyone serving on SGLang. Huge thanks to @modal and @sgl_project for the engine integration support!

Made some improvements on the decode path for MiniMax M3 by @MiniMax_AI on MLX-VLM Faster decode, slightly lighter footprint. Thanks to @ivanfioravanti for the PR 🚀 PR: github.com/Blaizzy/mlx-vlm/p…

Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇

GLM-5.2 is Fully Open, Frontier Intelligence Belongs to Everyone Today, the sudden restriction of certain frontier models is deeply regrettable. At a time when access to frontier models is abruptly cut off for non-technical reasons, we are even more convinced of one thing: science should be global. The path to AGI (Artificial General Intelligence) must never be enclosed by high walls. We have always believed that AGI should be the cornerstone for all of humanity to collaboratively explore the boundaries of intelligence and solve complex challenges, rather than a privilege monopolized by a few rules and subject to revocation at any moment. In the face of external blockades and restrictions, our attitude is one of radical openness. Frontier intelligence must remain open-source, accessible, and buildable, serving every dedicated developer. GLM-5.2 is Zhipu's most capable open-source model to date. It not only supports a truly usable 1M context window but also maintains a continuous lead in the independent completion of long-horizon tasks, providing solid foundational support for building complex agent applications. It also continues to be our main engine for creating the strongest domestic coding model. Tonight at 5:21—at this special moment—GLM-5.2 will officially be available to all GLM Coding Plan users (including Lite / Pro / Max). The API will also go live next week. A step closer to frontier intelligence for everyone. The future of AI is open, and it is for the people. ModelKey: GLM-5.2

Intelligence should be open, accessible, and ready to build with, empowering every developer, everywhere. GLM-5.2 is now available to all GLM Coding Plan users, including Lite, Pro, Max, and Team plans. docs.z.ai/devpack/latest-mod… As our new flagship model, GLM-5.2 delivers powerful coding capabilities, usable 1M-context support, and continued strengths in long-horizon tasks. API and Chatbot services will launch next week. The model will also be officially open-sourced next week under the MIT License. The future of AI is open, and it belongs to the people.

I just published One Metal kernel made Apple Core AI’s MoE decode 2–3.6× faster — same quality medium.com/p/one-metal-kerne…

Thanks for all the feedback. GLM-5.2 will begin rolling out to all Coding Plan users in 3 hours.

In light of the US government banning Fable for non US people (and Anthropic pulling it off cc) It’s more and more important that we develop systems that can’t be shut down, nor taken away. I’m grateful I got a glimpse of the future, I hope I get to spend more time with it

great fucking job, Anthropic incredible fear-mongering fuck progress, fuck science, fuck technology fuck the whole world except for US let's all go to the stone age together

Minimax-M3 is out!!!!!!! Good job on the Minimax team for making another banging open weight model. I knew it’d be 400B~ now to get it running

1 Billion Gaussians (1,035,804,128 exactly) streaming to the viewer at 60fps (vsync) and 5GB VRAM. There is no limit anymore to how much it can do. Some need a billion dollar corp to make similar things happen, others need paid pseudo influencers without skills and knowledge to make your software look bad because someone is shitting his pants. LichtFeld Studio is a product of love and passion. So help support this project by donating to it. 1B training on a single RTX 4090 will fall next. Ply -> rad took 28min which is not optimized yet. There is in general some more room for optimization. The dataset is just a 2x2 tile provided by: 3D scanning data created and provided by Andrii Shramko, TELEPORTOUR. Links in comment to the dataset provider!

🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced! 🔷 Improved coding & agent performance over K2.6: 21.8% on Kimi Code Bench v2, 11.0% on Program Bench, and 31.5% on MLS Bench Lite. 🔷 Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6. 🔷 Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates. ⚡️ 6x High-Speed Mode coming soon! 🔌 Available today via Kimi API and Kimi Code. 🔗 Kimi Code: kimi.com/code 🔗 API: platform.moonshot.ai

Everyone, please join Project Tapestry thealliance.ai/projects/tape…

just bring back gemini-2.5-pro-exp-03-25 release. That version would follow user instructions to the letter, never have any amnesia, and do amazing things over long context. that was gemini fable.

how can you praise this model as an AI researcher?

Already on MLX 🚀

🚀 Gemma 4 12B is here! We partnered with @GoogleDeepMind to bring and optimize their new dense and unifed multimodal model for Apple Silicon. ◈ 12B dense · 256K context ◈ Thinking mode (built-in reasoning) ◈ Vision: dynamic res, OCR, UI charts ◈ Native audio: ASR speech translation ◈ Function calling for agents ◈ Text image audio, interleaved Runs local. Get started now ⚡ > uv pip install -U mlx-vlm github.com/Blaizzy/mlx-vlm

Ok, but then there shouldn't be this "less than half the cost" language in the PR, even if hedged with "often". I'm not even searching for it btw, i only spot checked twice and both times it was ~double price of 3.1 Pro.