Tech Times

Compile Once, Run Offline: New AI Method Matches 32B Models With a 23MB File

Local AI inference at 32B-parameter quality, no cloud API required: University of Waterloo researchers released PAW on July 2 ...

Waterloo's PAW compiles task specs into 23MB LoRA adapters a 600M-parameter model runs entirely offline.

Local AI inference at 32B-parameter quality, no cloud API required: University of Waterloo researchers released PAW on July 2 ...
Decrypt

LongCat-2.0: The Stealth AI Model That Was Quietly Topping OpenRouter All Along

Chinese tech company Meituan officially unveiled LongCat-2.0 on June 30, confirming the open-license, 1.6-trillion-parameter mixture-of-experts AI model is the same system that sp ...

Meituan open sources LongCat-2.0, the 1.6T, near-frontier agentic coding model that's been leading OpenRouter — trained entirely on Chinese chips

By registering the LongCat-2.0 repository under the open-source MIT License, Meituan positions the architecture with maximum ...
GitHub

Let your AI agent query your Obsidian vault's knowledge graph directly

Your vault has a graph. But you can only stare at it. Obsidian's graph view is beautiful, but it can't answer questions — "Which notes have the most links?" "How many hops between these two concepts?" ...
GitHub

Prequel - C# SQL Query Engine

Prequel is a SQL query engine built in C#. The goal of this project is to demonstrate how query engines are built, and to bring a query engine to the .NET community. The project contains a ...