AIXplorethe lab
Special seriesComplete5 parts

DGX Lab

Building a working AI research lab on a single small box, from intelligent gateway to RAG stack to honest benchmarks.

What you can stand up on one small but powerful desktop AI box in a few days: a routing gateway where simple heuristics beat ML by a wide margin, a shell tuned for ML workflows, a complete local RAG stack from model to vector store, and a benchmark pass that separates the paper numbers from the production reality.

This is the homelab lineage that later de-risked far bigger borrowed hardware. Read it in order, day one through the wrap-up.

The series

All parts

  1. shipped14 min

    DGX Lab: When Simple Heuristics Beat ML by 95,000x - Day 1

    Building an intelligent AI gateway that routes requests 95,000x faster than ML while maintaining 90% accuracy—proving that smart heuristics can outperform deep learning.

  2. shipped10 min

    DGX Lab: Supercharge Your Shell with 50+ ML Productivity Aliases - Day 2

    Transform your default shell into a productivity powerhouse with GPU monitoring shortcuts, smart aliases, and custom functions—setup in 5 minutes, benefit forever.

  3. shipped16 min

    DGX Lab: Building a Complete RAG Infrastructure - From Ollama to Qdrant to AnythingLLM - Day 3

    Building a complete self-hosted RAG infrastructure with 8 integrated services on a single DGX workstation, supporting everything from medical AI fine-tuning to document Q&A.

  4. shipped12 min

    DGX Spark Benchmarks: 82,739 tokens/sec on Paper, the Production Reality

    NVIDIA's DGX Spark benchmarks show 82,739 tokens/sec for training. After 6 days of intensive ML workloads and feedback from the HN community, here's what the benchmarks don't tell you about precision issues, memory fragmentation, and production workarounds.

  5. shipped16 min

    My AI Linux Expert: How Claude Code Suggested a 95,000x Faster Solution

    When building an AI request router, my instinct was to use ML. Claude Code analyzed the test results, noticed the heuristics were already working, and suggested removing the ML model entirely—achieving 95,000x faster routing.

Follow the lab

Get the next experiment

Enjoyed the breakdown on DGX Lab? New entries land roughly weekly. No digest, no roundup. Just the next build log, when it ships.