devwithjevSimulates Text Attention
The build uses JEV to simulate the attention mechanism by approximating an attention score for each pair of words in a text. It treats texts as bidimensional entities.
Using JEV I simulated the Attention mechanism. On a text, for each pair of words I approximate the attention score. Texts are bidimensional entities!
https://t.co/Z68dqieDse https://t.co/kc5zhWG55e
Also filed under Research & data
- Jev Reranks Knowledge Search Results
You.com uses Jev through OpenRouter as a reranking layer for Knowledge in its Web Search API, selecting relevant results between retrieval and synthesis. The setup used 3x fewer tokens and achieved 84% accuracy on the Vertical RTK benchmark.
- Hermes Researches YouTube, X, and LN
Nabendu Biswas uses Jev in a Hermes agent to research YouTube, X, and LN.
- Visualizes French Wikipedia Elites
The project is a data visualization of French elites on Wikipedia. Its crawl is ongoing, with new biographies arriving.
- GraphRAG with Swappable Laya and Jev Models
This project is an agentic GraphRAG pipeline with swappable local Laya or cloud Jev decision models.