MCP App StoreThe latest from the AI and MCP ecosystem, curated daily.
Sources
A new approach to universal assisted generation that enables faster decoding across various assistant models, improving inference efficiency.
A comprehensive look at Aya Expanse, focusing on improving LLM performance across a vast array of languages. This pushes the frontier of multilingual AI and open-science data collection.
Introduction of SynthID Text, a tool for watermarking AI-generated text to improve detection and traceability. Critical for maintaining transparency and trust in AI-generated content.
Anthropic introduced Contextual Retrieval — a technique that prepends chunk-specific context to each piece of text before embedding, dramatically improving RAG retrieval accuracy. Combined with BM25 reranking, it reduced retrieval failure rates by up to 67% compared to standard RAG. A practical technique that any team using RAG with Claude can adopt today.