GoKawiil
Tech News
Industry sources describe software engineers increasingly unable to interpret code produced by large language models, with their jobs shifting from writing software to overseeing AI output. Infinity founder Jeremy Nixon and SemiAnalysis' Jordan Nanos cited examples, including OpenAI engineers reportedly unable to explain a GPU kernel generated for DeepSeek, despite the AI's code passing tests and performing correctly.
At Rails World 2026, David Heinemeier Hansson said he has retired as a professional programmer, calling himself a 'maker' who directs LLMs to write code in English rather than reviewing the output line by line. He said 37signals' next version of Hey will use LLM-generated Rust on the backend and native apps on each platform instead of the Rails-based web stack he has long championed, and claimed to have produced roughly 150,000 lines of code in August versus about 30,000 lines a year previously.
An essay draws a parallel between the historical shift in bridge construction from stonemasons hand-placing stone to carpenters building wooden forms for poured concrete, and today's shift in software development driven by AI code generation. The author argues developers are moving from directly writing code line-by-line, like stonemasons, to constructing structures such as tests, documentation and guardrails that shape what AI generates, akin to carpenters building molds.
A software engineer describes a personal experiment begun in February where they stopped writing code manually and instead relied entirely on AI coding agents like Copilot, Cursor, and Claude Code to implement changes. The account traces how tooling evolved from simple autocomplete suggestions to agents capable of editing multiple files from a single natural-language description, sharply reducing the amount of typing required.
A new industry analysis argues that as AI coding agents rapidly improve and handle longer tasks asynchronously, the traditional sequential product development pipeline—idea, product, design, engineering, QA, production—is being restructured. Implementation, once the dominant time cost in this pipeline, is shrinking, shifting the bottleneck to verification and simulation instead.