Blog

Blog

Explainer-style articles that go one level deeper than the news. how a specific technology or pattern actually works, and why it matters in practice.

Artificial Intelligence

How RAG Actually Works

A step-by-step walkthrough of retrieval-augmented generation: chunking, embedding, vector storage, retrieval, and grounded generation. and why it cuts hallucination rates in production systems.

ยท8 min read
Databases

Choosing Between pgvector and a Dedicated Vector Database

When native vector search inside PostgreSQL is enough, and when the scale or feature needs of a workload justify a dedicated vector database instead.

Systems

What eBPF Actually Lets You Do

A practical look at how eBPF programs run safely inside the Linux kernel, and why that unlocks observability and networking features that used to require kernel modules.

Open Source

Running Open-Weight Models Locally with Ollama

What it takes to self-host a capable open-weight LLM, the hardware trade-offs involved, and when local inference makes more sense than a hosted API.