Peter
1.1K posts
@NoDataSold
ai 🧠🌳💨 just one man smoking and taking to the earth and mind and ai and pain👨💻dealing with fibromyalgia 24.7 but could be worse. medical thc saves lives.
there's a lot of excitement around Kimi K3 so we are making it available immediately to OpenCode Go users we have not yet been able to negotiate a discount yet so it will currently consume your limits at a higher rate hopefully will figure this out soon
We've partnered with SpaceXAI to train Grok 4.5. It’s our most powerful model yet and the first we've built for more than software engineering.
🐱 LongCat-2.0 is now fully open-source — MIT licensed, no restrictions. Since our launch a few days ago, the response from the community has been incredible. Thank you for all the feedback, discussions, and interest. Today, we’re releasing the model weights and inference code to everyone. ◆ 1.6T MoE · ~48B active · 1M token context ◆ Agent-native: Integrates directly with Claude Code, OpenClaw, and Hermes Agent ◆ Deployment: Support both GPU and NPU platforms— verified on large-scale domestic clusters 📑 Tech Blog: longcat.ai/blog/longcat-2… 🤗 HuggingFace: huggingface.co/meituan-longca… 💻 GitHub: github.com/meituan-longca… 🪄 ModelScope: modelscope.ai/collections/me… 👇 Inference Code GPU: github.com/sgl-project/sg… NPU: github.com/meituan-longca…
yeah this is where it starts getting fun. this morning’s journey log: getting hermes running with mixture of agents across 2 dgx sparks. one spark gets qwen. one spark gets nemotron. then hermes sits in the middle and uses both instead of me depending on one model to handle everything. that’s the part i’m testing this morning two boxes on my desk, a bunch of local models, and me trying to see how far i can push this thing. local ai is starting to feel less like “run one model” and more like building your own little team of brains.
