Burkov Asks: Would Switching From Python to Rust or C Hurt LLM Coding Ability?
burkov · x · 2026-09-24
Andriy Burkov, author of The Hundred-Page Machine Learning Book, says he can't find any recent, reliable comparisons of how well frontier LLMs code in different programming languages.
His reasoning: if he hasn't read code in a year without issues, why keep Python as an app's base language instead of switching to C, Rust, or whatever is fastest? But he isn't willing to tolerate a drop in the LLM's problem-solving capacity from a language change, and is asking for convincing research or benchmarks on the question.
More from coding & agent
- Real-Time Writing Linter Flags 'LinkedIn-Speak' and Prints Violations on a Receipt Printer — jh3yy · 2026-09-24
- zlaya: a Zig-based CPU-only inference engine runs Laya on CDN edge via WebAssembly — jedisct1 · 2026-09-24
- DiffusionGemma triages outages in ~180ms on a single serverless L4 GPU — rseroter · 2026-09-24
- Opus 5.5 has been autonomously improving an open-world NYC game for nearly a day — mattshumer_ · 2026-09-24
- This AI writing linter flags LinkedIn-style prose and prints receipts in real time — jh3yy · 2026-09-24
- A developer reportedly set the record for the most expensive single Claude run — mattshumer_ · 2026-09-24