The "imaginary" part of RoPE contains valuable information for long-range dependencies RoPE++ reintroduces it in heads with slower decay curves that better capture distant tokens We provide implementations with one-command scripts for both the original codebase and Nanochat!
INNOVATION
-

AI Scientist: Game Changer Tool for Research Automation
By
–
ok this is going to be game changer for me the "AI Scientist"
-

Edge AI gesture control brings smart home automation to life
By
–
Wave your hand. Dim the lights. David Katus’s Project Gaius will bring gesture-based smart home control to life; all powered by edge AI and running fully offline. A hands-free, intuitive future starts here. https://
eu1.hubs.ly/H0qP2w40
#EdgeAI #GestureControl #SmartHome #HMI -
AI Industry Leadership and Partnerships Define 2025
By
–
2025 was an important year when different industries with different missions all focused on one thing: AI that actually works. Our biggest moments were about deep partnerships that translated to industry leadership, bold conversations and best practices. Here's to 2026! pic.twitter.com/9FpcOR2PAu
— Domino Data Lab (@DominoDataLab) 8 janvier 20262025 was an important year when different industries with different missions all focused on one thing: AI that actually works. Our biggest moments were about deep partnerships that translated to industry leadership, bold conversations and best practices. Here's to 2026!
-
Apache 2.0 Licensed Model Available on AI21 SaaS and Hugging Face
By
–
4/4 Licensed under Apache 2.0 and available today on AI21 SaaS and Hugging Face:
-

Top 6 Essential AI Skills for 2026 and Beyond
By
–
Top 6 AI skills for 2026 • Prompt engineering
• Workflow automation
• AI video creation
• RAG systems
• Vibe coding
• AI search optimization The edge isn’t tools.
It’s systems + execution. #AI #GenAI #FutureOfWork #Automation -

AI and Energy Constraints: Efficient Inference at CES 2026
By
–
One thing that stayed with me from #CES2026 is how closely AI and energy are now linked. Many of the discussions focus on constraints and how to overcome them: efficient inference hardware, more processing done locally instead of in the cloud, and a more realistic view of what
-

Roborock Rover Robot Vacuum Now Climbs Stairs While Vacuuming
By
–
Your robot vacuum just learned a new life skill: stairs. The Roborock Rover doesn’t politely stop at the edge anymore.
It climbs. While vacuuming. Like it suddenly decided gravity is a suggestion. It’s funny, but also telling.
For years, home robots were optimized for perfectly -

Small Models Over Large: Efficiency and Memory Footprint
By
–
Reject big models, embrace small memory footprint
-
Write High-Performance Hardware Kernels in Python with Pallas
By
–
You no longer need to leave Python to write high-performance hardware kernels. Learn how to use Pallas in Keras to author custom ops that lower to Mosaic for TPUs or Triton for GPUs:
