What 150 replies taught about agent languages: Rust beats Python for AI-written code
fhinkel · x · 2026-10-21
fhinkel polled X on what language your agent should write in if nobody reads code anymore. Across nearly 150 replies, Rust came first, followed by TypeScript, Python, C/C++, Java/Kotlin, Go, and Wasm.
Key insight: when you're not typing every character yourself, syntax ergonomics matter less than verification loops. A strict compiler or static analyzer cannot be sweet-talked by a model — a Rust borrow checker error, TypeScript type mismatch, or clang-tidy rule gives the agent an unambiguous diagnostic it can fix in its own loop before escalating to a human. Compile times and day-two operations pull in the opposite direction.
The piece captures a fundamental shift in how language value should be ranked in the agent era: verifiability over writability.
Related event: Rust Beats Python as Top Language Choice for AI Agent Coding Era(2 posts)→
More from coding & agent
- Laude Institute launches Slingshots FOUR: 14 projects across 8 top institutions — a1zhang · 2026-10-21
- Research agent Épi sets 120 records, narrows n-queens constant interval 84x — dair_ai · 2026-10-21
- Compaction hooks in practice: keep last n messages verbatim, summarize the rest for full agent continuity — MoonL88537 · 2026-10-21
- The blank prompt box hides real operational burden: context, workflow and supervision fall on users — _AustinCalvert_ · 2026-10-21
- DeepMind paper: self-evolving agents forget as they learn — fastest learner GEPA also breaks old tasks most — rohanpaul_ai · 2026-10-21
- arXiv: Are Self-Evolving Agents Continual Learners? Plasticity comes at the cost of stability — rohanpaul_ai · 2026-10-21