Tag
A new compute layer where distributed consensus serves as the core computation mechanism, not just a record-keeping tool.
A novel parser architecture developed by Shanshrew achieves 2-3x speedup over the current fastest JS/TS parser, and is being integrated into Oxc.
A student introduces Silia, a novel transformer architecture that combines attention and FFN into a unified operation to save parameters at scales ≤10M, achieving comparable performance to GPT-2 with fewer parameters despite limited compute resources.
Introducing Gemma 4 12B, a multimodal model supporting audio, image, video, and text input with a novel unified architecture and a new MacOS desktop app powered by LiteRT.