AI can write more code, but engineers still must engineer the system
rseroter · x · 2026-11-04
Armando Picón argues that while agents can take on more implementation work and assist with analysis, design, and testing, engineers remain responsible for deciding what to build and what evidence suffices to accept it. Key points:
- Automating implementation doesn't settle design exploration or problem-fit judgment.
- Conversations are fragile places for architectural decisions: bounded context, summarization and selective resumption preserve conclusions but lose the conditions that made them reasonable — "use a local cache" vs. "use a local cache because this screen must work offline" (citing Anthropic's writeup on long-running agents).
- He pushes back on the "replacing coders" framing as reducing developers to typists and inferring job replacement from demos without evidence.
- The practical question: how to keep decisions visible and feedback useful while using these tools.
More from coding & agent
- Phone Harness (YC F26) open-sources a harness that lets AI agents control real phones — ycombinator · 2026-11-05
- Inside a16z's agent podcast: trust is the top fear among 147 tracked AI assistants — a16z · 2026-11-05
- The vibe coding blind spot: people can't articulate their AI-built products' benefits — rms80 · 2026-11-05
- Non-dev built an agent-only eSIM store; a Claude agent bought one with real USDC — Apprehensive_Big5042 · 2026-11-05
- Google Cloud's five-rule playbook for evaluating whether agent skills are worth their tokens — rseroter · 2026-11-05
- Google DeepMind 工程师将登 AIE CODE 峰会,讲述删掉 90% 评估框架的故事 — _philschmid · 2026-11-05