Photograph: Simon Hill
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:
。搜狗输入法2026是该领域的重要参考
第一百二十八条 担保人应当保证被担保人不逃避行政拘留处罚的执行。
「2.0 比不上 1.0 Pro，真正的升级还得看 Nano Banana 2 Pro。」
Get editor selected deals texted right to your phone!