AI replaces engineering
The recurring fantasy that the next model — or low-code, or codegen — eliminates the need for people who own production outcomes.
AI-replaces-engineering is low-code with a chat box and better demos. The pitch: natural language will translate requirements into systems, shrinking headcount and "democratizing" building software. The reality: edge cases, security, integration, and accountability remain, and they concentrate in the senior engineers you still need when the demo hits prod.
Copilot-style tools genuinely help with boilerplate and exploration. They also hallucinate APIs, skip tests, and optimize for plausible diffs rather than correct behavior. Pilots that feed LLMs a snippet and ask for a rewrite fail the same way big-bang rewrites always fail — unknown legacy context, missing parity checks, political ownership of modules nobody wants to touch.
History rhymes: 4GL tools, CASE environments, "citizen developer" platforms — all promised to remove engineering until governance and exceptions pulled engineers back to untangle the graph. AI raises the floor on typing speed and lowers the floor on verification discipline if leadership believes the hype.
The durable pattern is augmentation with ownership: humans accountable for prod, migrations in slices, tests as contracts. Anything else is procurement theater — impressive until regulators, customers, or 2 a.m. pages ask who signed off.
Exhibits
Practice · 2023–now
AI will rewrite the codebase
Big-bang rewrite, now with a chatbot. Same failure mode; prettier slides.
$ Exec decks promised autonomous migrations "by next quarter." Teams that skipped tests, ownership, and incremental strangler patterns bought expensive demos and fragile diffs.
Practice · 2021–now
AI pair programming
Autocomplete that actually understands the file. Changing how code is written faster than how it's reviewed.
Framework · 2023–now
LLM app frameworks
Chains, agents, and prompt wrappers shipping weekly. The durable pieces will be boring: evals, retrieval, and product UX.
Practice · 2018–now
Low-code will replace eng
Drag-and-drop apps for the enterprise backlog. Useful for internal tools; fantasy as a full replacement for engineering.
Practice · 1995–now
Big-bang rewrite
Replace the working system instead of strangling it. A perennial money pit with new branding each decade.
$ "We'll freeze features and rewrite in the hot language." Multi-year projects shipped late, incomplete, or not at all — while competitors iterated on the ugly system that made money.
Practice · 2023–2024
AutoGPT-class autonomous agents
Give the model a goal and a credit card. Viral in 2023; quietly shelved when the loop never stopped spending.
$ Open-ended agent loops burned API credits chasing goals nobody specified well enough to finish. Demo videos outpaced production deployments by orders of magnitude.
Practice · 2024–now
Vibe coding
Accept AI output on feel, skip the diff, hope tests exist. Fast demos; fragile ownership.
$ Ship-to-prod without reading the diff became a flex until incidents revealed nobody knew which prompt wrote the auth middleware. Review debt arrived in one weekend demo.
Framework · 2023–now
Multi-agent orchestration hype
LangGraph, CrewAI, AutoGPT cosplay — agents delegating to agents for tasks one function call could do.
$ Autonomous agent swarms burned API budgets on coordination loops that a single prompt and a cron job would have handled. Debugging "which agent lied" became the new on-call sport.