π ⅃
6K posts
@PeterEloy
when i do it, it looks ez @open_d_app creator | T1D for 35 years
Today we’re releasing Qwen-Scope 🔭, an open suite of sparse autoencoders for the Qwen model family. It turns SAE features into practical tools： 🎯 Inference — Steer model outputs by directly manipulating internal features, no prompt engineering needed 📂 Data — Classify & synthesize targeted data with minimal seed examples, boosting long-tail capabilities 🏋️ Training — Trace code-switching & repetitive generation back to their source, fix them at the root 📊 Evaluation — Analyze feature activation patterns to select smarter benchmarks and cut redundancy We hope the community uses Qwen-Scope to uncover new mechanisms inside Qwen models and build applications beyond what we explored.Excited to see what you build! 🚀 🔗🔗 Blog: qwen.ai/blog?id=qwen-s… HuggingFace: huggingface.co/collections/Qw… ModelScope: modelscope.cn/collections/Qw… Technical Report: …anwen-res.oss-accelerate.aliyuncs.com/qwen-scope/Qwe…
We are not an AI wrapper. Most “AI diabetes tools” are just ChatGPT with a nice skin: You type → generic answer. In T1D that’s risky. Here’s what actually makes Open-D different 👇
Before that alert fired, the prediction model verified the trend 3 times. We're now testing a 2-check shortcut for extreme lows - faster intervention when speed matters most.
We rewrote the onboarding from 3 steps to 9. Split Toujeo from Tresiba at the insulin level. Rebuilt pharmacokinetics from exponential decay first principles. v1.7.2. Zero TS errors. Schema v28. Rigor first. Launch later. This is Open-D. open-d.app 💉🧠 #T1D
