Three classes of programming languages in the AI era: natural language, performant code, and specs
dbreunig · x · 2026-11-16
dbreunig argues future programming languages will split into three classes: natural language (imprecise, written for humans), performant code (stable, safe, fast, written by computers like Rust/Go), and 'Goldilocks specs' that are more precise than natural language yet more readable than performant code (Python, TypeScript, Ruby).
He contends the third class is critical but underdiscussed: without it, natural language must absorb all specificity requirements (engineers writing exacting prompts) and/or performant code must compromise for humans.
More from coding & agent
- Turning newsletter edits into AI checks lifts frontier models 25+ points on summaries — danshipper · 2026-11-16
- WEKA open-sources kvlab: replay real agent traffic to benchmark KV cache offload — AccBalanced · 2026-11-16
- levelsio runs every business on VPS servers managed solely via SSH and Claude Code — alvelda · 2026-11-16
- Dev builds remote MCP server with inline MCP Apps video player for 5,500 meme clips — Mediocre-Number-5498 · 2026-11-16
- Developer's autonomous "factory" builds usable app for ~$40 in Claude credits — threepointone · 2026-11-16
- 20-year AI veteran curates 19 free open-source repos for building AI agents — MaryamMiradi · 2026-11-16