Research & Insights

What we're thinking about

Technical writing, architecture decisions, and honest assessments of AI tooling from engineers who build with it daily.

157 articles published

Featured

Tools

Cursor vs Claude Code in April 2026: What Actually Changed

Our original Cursor vs Claude Code comparison got valid pushback — Cursor has shipped agent mode, subagents, a CLI, cloud agents, and terminal access since we wrote it. Here is the corrected picture as of April 2026, with what actually matters for choosing between them now.

Read articleApr 8, 2026 · 8 min read

157 articlesLatest first

APR152026

AI & Engineering15 min read

AI Agent Architecture: Production Patterns from the Field

Building an agent that works in a demo takes a day. Building one that runs reliably in production for six months takes a team. These are the architectural patterns that separate the two.

APR152026

AI Strategy8 min

The Complacency Gap: What Switching AI Coding Tools Taught Me About Vigilance

Switching from Claude Code to Codex felt like cognitive load returning — slower, less comfortable, more effortful. Then I realized that load was not a cost. It was the work. A reflection on automation complacency, context decay, and what the right relationship with AI coding tools actually looks like.

APR152026

Explainer5

Prompt Injection Explained for People Who Don’t Write Code

Prompt injection is the AI version of social engineering: instead of hacking the system directly, an attacker tricks the model into following bad instructions. If your product uses AI to read, search, summarize, or take actions, this is a business risk, not just a technical one.

APR152026

AI News5

Who Is Winning the AI Race Right Now (Week of April 15, 2026)

Updated model scorecard for the week of April 15, 2026. Anthropic holds the lead, Google is accelerating faster than anyone admits, and OpenAI is watching its agentic coding story get complicated by a convergence nobody planned.

APR142026

Weekly Roundup5

5 Things in AI This Week Worth Your Time — April 14, 2026

Meta is restructuring around AI-built code, multi-agent development inherits distributed systems failure modes, and LinkedIn's economics chief just labeled software engineers as highly vulnerable. Five stories worth your time this week.

APR142026

Engineering7

Before You Deploy an AI Agent: 12 Things Engineers Skip

A practical pre-deployment checklist for AI agents — 12 things most engineering teams consistently skip that will bite them in production.

APR142026

AI News4

Linux Just Settled Its AI Code Debate — Here's What It Actually Means

The Linux kernel team just formalized its AI coding policy. Copilot and Claude Code are allowed — but every line you submit is yours to own. Here is what it means for every engineering team that hasn't figured this out yet.

APR132026

Opinion12

AI Benchmarks Are Broken and Nobody Wants to Admit It

SWE-bench scores keep climbing, marketing decks keep citing them, and production AI keeps disappointing. After 14 years of watching the software industry worship vanity metrics, I am calling it: AI benchmarks measure benchmark performance, not real-world capability.

APR132026

Engineering12

How to Add Streaming AI to Your Next.js App Without a Surprise API Bill

A step-by-step guide to building streaming AI features in Next.js with the Vercel AI SDK — including the token limits, error boundaries, and cost controls that tutorials skip.

APR132026

Tools6

ROCm vs CUDA in 2026: After Testing Both, Here's the Truth

AMD's ROCm is finally a real CUDA alternative in 2026. But "real alternative" and "drop-in replacement" are very different claims. Here's what actually works, what doesn't, and who should switch.

Showing 10 of 157