HNHiroyuki Nakahatainblog.iroha1203.dev·6h ago · 15 min readThe Rising Sea of Software Engineering — Rebuilding the Discipline on Algebraic GeometryAI now writes code faster than humans can review it. That is not a prediction; it is the daily experience of most engineering teams. And here is the other daily experience: no matter how much you inve00
PKPatrick Kearnsinfullstackcity.com·16h ago · 18 min readWhat If Your Pull Request Had a Blast Radius Score?Some pull requests look harmless until they reach production. Then someone notices the change touched authentication, a shared response contract, an EF Core migration, and one production config value 00
OKOleh Keminblog.comparedge.com·12h ago · 7 min readChoosing an LLM API for production in 2026: not benchmarksLeaderboards are a bad procurement tool A model can win a benchmark and still be wrong for your production system. Production asks less glamorous questions. How fast is the first token? What happens t11M
JOjose orgueirainjorgue.hashnode.dev·13h ago · 4 min readAI Didn't Make Me a Better Programmer. It Gave Me Time to Build Better ProductsWhenever people talk about AI-assisted development, the conversation almost always starts with the same question: "How much faster can you write code?" After spending the last few months building a re00
HPHarikrishnan PHinhariph.hashnode.dev·14h ago · 5 min readIn multi-agent systems, the skill is the abstraction level — not the agent countEveryone building multi-agent systems knows the starting pattern by now: a router reads the request, works out what's actually being asked, and dispatches to specialized agents — one to set up the pro00
JVJason Vertreesinjvertrees.hashnode.dev·6h ago · 14 min readThe AI-Native Way to Organize Software WorkCaveat lector: this post is a reflection on what I've predicted and am currently seeing in my work. As we all learn more during this AI transition, these thoughts might mature and change. About a year00
JVJason Vertreesinjvertrees.hashnode.dev·8h ago · 3 min readThe problem with "does this look right?"LLM-as-a-judge means using one model to check another model's output — usually because manual review doesn't scale. It sounds like an obvious fix. In practice, a naive version of this check fails in t00
RKRemco Koedootinremcokoedoot.hashnode.dev·1d ago · 5 min readSpec-Driven Development: Capture Intent Before You BuildThe most expensive line of code is the one that implements the wrong thing perfectly. It compiles. The tests pass. It does exactly what the ticket said. And it solves a problem that was not the actual00
AOAdekola Olawaleinadekolaolawale.hashnode.dev·17h ago · 6 min readPart 1: What Does a Staff Frontend Engineer Actually Do?Ask ten developers what a Staff Engineer does and you'll probably receive ten different answers. Some will say: "It's basically a Senior Engineer with more experience." Others will say: "They're ar00
FAFaizan Aliinmadprogrammer1.hashnode.dev·21h ago · 6 min readScalability Explained: What It Really Means to Build Software That GrowsFrom Code to Scale — Part 1 Every developer eventually hears someone say: "We need to make the application scalable." It sounds straightforward. Until you ask the obvious question: What exactly is 00
