It turns out you can achieve pretty decent performance with far less memory! All you need is this clever new primitive called Cartridge—a pretrained key-value (KV) cache designed to replace the expensive runtime memory footprint of in-context learning (ICL) for large corpora
SOFTWARE
-
RP1 Launches World’s First Metaverse Browser
By
–
RP1 Launches the World’s First #Metaverse Browser –
-
Barclays Scales MS365 Copilot to 100,000 Employees
By
–
Microsoft announced that Barclays is scaling MS365 Copilot to 100,000 employees
— Rowan Cheung (@rowancheung) 10 juin 2025
The move is one of the largest known deployments of generative AI in the banking sector to datepic.twitter.com/OefS2VrtVuMicrosoft announced that Barclays is scaling MS365 Copilot to 100,000 employees The move is one of the largest known deployments of generative AI in the banking sector to date
-
Apple’s Limited AI Features Unveiled at WWDC 2025
By
–
At WWDC 2025, Apple showed off only a handful of AI upgrades, including: —New Live translation for FaceTime, Messages, and calls
—Visual intelligence via screenshots —AI-powered intelligent actions in Shortcuts
—AI "Workout Buddy" on Apple Watch -
FactoryAI Credits and Vim Editor Programming Tools
By
–
yeah, I thought about leaving him some @FactoryAI credits and telling him "I'm sorry that @ThePrimeagen got you into vim".
-
Pure Storage CEO on Software-Driven Data Storage Evolution
By
–
Please enjoy my interview with Pure Storage CEO Charlie Giancarlo. Pure Storage CEO: The software story evolves For data storage vendor Pure Storage, a steady stream of new software features is pushing a stodgy corner of IT ever deeper into the software-as-a-service realm.
-
AReaL: Asynchronous Reinforcement Learning System for Language Reasoning
By
–
AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning AReaL is an asynchronous reinforcement learning system that efficiently trains large language models for reasoning tasks by maximizing GPU usage and decoupling generation from training.
-
SmolVLA: Efficient Vision-Language-Action Model for Robotics
By
–
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics SmolVLA is a compact, open-source VLA model built for low-cost training and real-world deployment on consumer hardware, enabling efficient language-driven robot control without sacrificing performance.
