Advanced RAG
AI infrastructureDeeper RAG techniques — hybrid retrieval, reranking, chunking strategies, and evaluation — for building retrieval pipelines that hold up in production.
AI Agents · Systems Design · Low-Level Engineering
Engineering explainers, written to be cited
AI Agents · Systems Design · Low-Level Engineering
Latest articles
All articles →AI Watermarking Just Changed the Rules, and Open Models Make It Messy
Anthropic now embeds an invisible watermark in Claude's text at the moment it's generated — not metadata, but a pattern baked into word choice itself. Here's how that works, what it means for SEO, and why open-weight models can't be forced to carry the same signal.
- Aug 11, 2026
What's Actually Inside an AI Agent
Tool calling, orchestration, memory, tracing, guardrails, agentic workflows. Underneath all of it is a loop that fits in about fifteen lines of code, plus everything you need to keep it alive once real users show up.12 min - Aug 5, 2026
What Is CUDA, and Why Does GPU Programming Create Vendor Lock-In?
CUDA isn't a language, it's NVIDIA's whole GPU computing platform. Here's what a kernel launch actually does, how threads and blocks work, and why deep CUDA usage becomes so hard to leave.14 min - Aug 3, 2026
Building a Cache-Augmented Generation System From Scratch
I built cache-augmented generation the slow way, no LangChain, no vector database, no hosted API. Just PyTorch, a 0.6B model, and a GPU, to see exactly what KV cache reuse does under the hood.14 min - Aug 1, 2026
What RAG Actually Is (and Why Your LLM Doesn't Know Your Company Data)
RAG lets an LLM answer questions about your private company data without retraining it. Here's how retrieval, embeddings, and generation actually fit together under the hood.6 min - Jul 30, 2026
Tokens! What They Actually Are
Tokens aren't words — they're subword units a tokenizer learns from raw text. Here's how that actually works.3 min
In progress
Voice Agents
Conversational AIExploring voice-powered AI agents — from speech recognition and synthesis to building end-to-end conversational systems that understand, reason, and respond naturally.