Articles
In-depth articles on AI, web development, cloud native, and indie hacking.
Writing business rows and events separately to a database and message system creates a dual-write window, while a send timeout cannot prove that the message was not delivered. This article combines outbox events, dispatcher claims, unknown-delivery reconciliation, and consumer deduplication into an auditable protocol.
Testing agents is harder than ordinary software—non-deterministic, multi-step, with external tools. This article gives a layered strategy: unit tests for tools, integration for end-to-end, evaluation sets for quality, chaos for fault tolerance, plus trace reproduction and regression. Turn "launching on luck" into "launching with confidence".
Type declarations do not validate network, Worker, URL, IndexedDB, or cross-tab messages. This article converts unknown input into canonical internal types and designs schema evolution, dual-read rollouts, and rollback paths for legacy data.
Full-parameter fine-tuning can require dozens of GPUs, while LoRA and QLoRA bring it within reach of a single consumer card. Learn low-rank adaptation, 4-bit quantization, the full workflow from data preparation through deployment, and when fine-tuning is actually the right solution.
Uniform sampling by frame number misreads variable-frame-rate video and misses brief events. This article creates reproducible video inputs with a canonical timeline, layered sampling, scene-change additions, audio-video alignment, and temporal regression gates.
AI framework choices are unavoidable, but LangChain, LangGraph, and LlamaIndex are often complementary, not competitors. This article maps their roles: full-stack glue, agent orchestration, and data/RAG; explains how to choose; and covers an underrated option: using no framework and writing it yourself.
A small image file does not necessarily make vision inference cheap, while resizing everything to a fixed size can erase fine print. This article establishes verifiable resolution budgets using task slices, pixel tiers, targeted region rereads, and actual billing data.
AI apps are data black holes—user input, model calls, training retention all hide landmines. Covers four compliance essentials: user input data, model data handling, fine-tuning data provenance, and cross-border and industry compliance (GDPR/healthcare/finance), plus privacy-first engineering to keep your product off legal red lines.
Web Locks can serialize same-origin tabs entering a critical section, but they do not provide fencing tokens for server writes. This article separates browser leader election, persistent generations, and side-effect commits to prevent stale tabs from overwriting current state.
AI products face a problem traditional software doesn't: every user generates variable token cost. Price it wrong and you lose money or drive users away. This article breaks down five mainstream AI pricing models — pay-per-use, subscription, credits, value, hybrid — their fit and pitfalls, and how to break the trap of losing more as usage grows.
A 2xx response proves only that an endpoint successfully answered an HTTP request, not that the subscriber completed business processing. This article uses subscription generations, a signing-key state machine, immutable delivery evidence, and optional processing receipts to govern retries and rotation.
Vector search excels at semantic similarity but struggles with relationship reasoning such as reporting lines and product dependencies. Knowledge graphs fill that gap. This article explains their advantages over vector databases, how GraphRAG works, when graphs are worthwhile, and pragmatic ways to adopt them.