However, due to modern LLM postraining paradigms, it’s entirely possible that newer LLMs are specifically RLHF-trained to write better code in Rust despite its relative scarcity. I ran more experiments with Opus 4.5 and using LLMs in Rust on some fun pet projects, and my results were far better than I expected. Here are four such projects:
Филолог заявил о массовой отмене обращения на «вы» с большой буквы09:36
。关于这个话题，爱思助手下载最新版本提供了深入分析
Всего, по предварительным данным, в центре города прогремело три взрыва. Несколько ракет попали по университетской улице и району Джомхури.。一键获取谷歌浏览器下载是该领域的重要参考
Google publicly documented its roadmap. This is what it says:
Kevin Church/BBC News