A personal blog by Abdur Rafay. Documenting things I build, engineering notes, university experiences, and ideas along the way.
Recent posts and articles
What happened when I fixed reflection blind spots, resolved sandbox import bugs, and scaled Patchwork from 3B (60%) to 7B (76%): which bugs were agent flaws, which were model limits, and how confirmation bias shrank.
How an execution-guided LangGraph reflection loop boosted a 4-bit Qwen2.5-Coder-3B model from 38% Pass@1 to 58% Pass@overall, and the confirmation-bias blind spot it uncovered.
Engineering an asynchronous LangGraph pipeline with Groq 20B/120B dynamic routing, Qdrant vector retrieval, and thread-offloaded cross-encoder reranking.
Browse articles by topic