SIGN-AIR: real-time sign language recognition and translation using gesture-aware neural networks on aerial robotic platforms

Introducing Hy4 Preview

Introducing Hy4 Preview New open weight text input (no vision) LLM from Chinese company Tencent today: 770B total parameters, 49B active parameters, 1M token context window, 1.56TB on Hugging Face .

• Tencent unveils Hy4, a 770 billion parameter LLM with 49 billion active parameters.
• Context window of Hy4 extends to one million tokens, a significant increase from Hy3.
• Hy4 offers only two reasoning effort levels: high and nothink.

8h ago ·simonwillison.net

A Finding Is Not a Discovery

This is the first contest I have entered. I built the honesty controls before I built the agent, which is probably backwards for a hackathon and exactly what I wanted to learn from.

8h ago ·dev.to

Microsoft Strips Copilot's Free Features — and Puts Deep Research Behind a Subscription

Open the Microsoft Copilot app this week and it may be missing a few things you used. As of 18 August, Microsoft began retiring a clutch of free consumer features — the standout being Deep Research…

• Microsoft removes free features from Copilot app
• Deep Research replaced by Researcher for $19.99/month
• Users must manually save and retrieve content before 18 August deadline

8h ago ·dev.to

How Many AI Avatars Can One GPU Handle? Real-World Test Reveals 4 Avatars at ¥7,600 Each per Month

📝 Originally published (in Japanese) at forge.workstyle.tech . Building an Unmanned System for 3D Avatar Live Streaming We're developing an unmanned system where 3D avatars automatically handle live…

• A single GPU can support four 3D avatars in live streaming
• System reliability improved with automatic host switching
• Startup speed reduced from four minutes to 95 seconds

8h ago ·dev.to

AI Creates, AI Delivers, AI Fails — Quality Assurance for Unwatched Systems

📝 Originally published (in Japanese) at forge.workstyle.tech . Building a Fully Automated AI Avatar Streaming System on YouTube and Twitch I built a system that lets AI avatars stream continuously on…

• Traditional testing assumptions don't apply to unmanned AI streaming system
• Focus shifted from output correctness to system behavior and guarantees
• Human intervention needed for certain bugs despite extensive automated testing

7h ago ·dev.to