https://danorlando.com/blog How-to's, discoveries and other useful nuggets fit for developer consumption. en-us undefined (Dan Orlando) undefined (Dan Orlando) Thu, 16 Apr 2026 00:00:00 GMT https://danorlando.com/blog/genai/retrieval-as-generation https://danorlando.com/blog/genai/retrieval-as-generation An 8B-parameter model matches GPT-4o across five knowledge-intensive benchmarks and beats it on two. It does this by replacing the entire retrieval orchestration layer—confidence classifiers, query routers, rerankers, fusion logic—with four special tokens. No external components. When it fails, you read a transcript. That's the whole debugging story. Thu, 16 Apr 2026 00:00:00 GMT undefined (Dan Orlando) genairagagentdesign