Recent articles
Insights on modern web development, performance, and building better digital products.
Kimi K2.6: An Open-Weight Frontier Coding Model at One-Tenth the Cost
Moonshot's Kimi K2.6 is the second open-weight Chinese coding model to land at frontier level in four months. For agencies shipping AI agents to clients, the stack decision changed overnight.10 min readRotate, Redeploy, Revoke: The webvise Response to the Vercel Breach
Vercel disclosed a supply-chain breach on April 19, 2026. The response I ran across every managed project, and why this breach shape needs a different response model.7 min readHermes Agent in Production: the Day-30 Problem
Most Hermes Agent 4-profile teams work on day one and show signs of voice convergence by day 30 in production deployments. The operator layer that prevents it: handoff contracts, memory-KPI audits, and policy gates per role.9 min readWhy Most AI Agent Setups Run Far Slower Than They Could
The architecture around the model explains the gap between modest and substantial AI productivity outcomes. Five builders published the same thesis in one week.9 min readThe AI Knowledge Layer: 127 Pages, Zero Vector Databases, and What I Got Wrong
Karpathy's LLM wiki gist hit 99,000 bookmarks in a week. It resonated because it named what every AI user feels: your agents have no memory. I run a knowledge layer in production. Here is what works, what does not, and how to build one in 20 minutes.8 min readFrom Rules to Results: What 22K Stars on a Single CLAUDE.md Reveal About AI-Assisted Development
The karpathy-skills repo proves that AI coding bottlenecks aren't about model capability. They're about the behavioral contract between human and LLM.7 min readMost Business Knowledge Bases Do Not Need RAG
I run my internal wiki on five shell commands and a hand-maintained index file, no vector database. For a 200-document knowledge base, that setup is cheaper, faster to build, and more accurate than a RAG pipeline. Here is why I skipped RAG and when you actually need it.8 min readClaude usage limits: 10 checks before you upgrade
Check which Claude limit you reached, keep useful context, and measure one task before buying more capacity. Includes a task brief from the webvise workflow.7 min readoh-my-claudecode and oh-my-codex: How Multi-Agent Orchestration Is Changing AI-Powered Development
Two open-source projects turned Claude Code and OpenAI Codex CLI from single assistants into coordinated agent teams. Here's how oh-my-claudecode and oh-my-codex work, what they enable, and why multi-agent orchestration matters for professional development.11 min read