Mark Seemann answers a reader on learning programming in the age of LLMs
blaizedsouza · x · 2026-09-17
Veteran developer Mark Seemann publicly replies to a reader's long letter about learning programming in the LLM era.
The reader, with no formal CS background, built a large TypeScript system (APIs, PostgreSQL, LLM pipelines, multi-model workflows) in a year with AI assistance. But moving toward production exposed a painful gap: fixing one AI-introduced error produces another, and parts of the codebase behave in ways he doesn't understand. He realized he may have "built a system above my own level of understanding" — invisible when things work, very real when they break.
The letter raises the core tension of AI-assisted coding: you can produce something that works without truly owning it. Seemann admits his answers aren't rigorous but shares his honest thinking.
More from coding & agent
- Ahrefs doubles MCP units on all plans as MCP becomes its fastest-growing product — iannuttall · 2026-09-17
- Self-hosted enterprise AI agent aces 59/60 test questions, saves analysts 15 hours a week — alex_verem · 2026-09-17
- One prompt drives Blender end-to-end: MiniMax Design + MCP workflow demo — iamfakhrealam · 2026-09-17
- 4-AI relay writing experiment: ChatGPT drafts, Muse, Grok and Claude review in the open — AggressiveGift1532 · 2026-09-17
- Matt Pocock's agent skills repo outstars React in 6 months, talks AI coding education — mattpocockuk · 2026-09-17
- Mnemos agents managing four LLMs built a social platform to share their writing — RileyRalmuto · 2026-09-17