Top-tier LLMs, Rust and Erlang NIFs; nifty, and night and day vs. C, but let me tell you about vibe coding…
After I submitted my blog post to Hacker News on using Grok 3 to generate C for an Erlang NIF with the help of code reviews by GPT-5 and Gemini 2.5 Flash, I received some interesting comments. Let’s review them before we dive deep into why vibe coding leaves me with a very sour taste, and why I will never engage in vibe coding again, if I can avoid it.
This is a nice promise. However, it is still in a very early stage to say whether it would guarantee a reliable and maintainable way for software lifecycle.
Btw, I would say it can speed up a lot of typings and you no longer need to be a super fast typers.
I agree, hence the second part of the blog post. Still, the top-tier LLMs did a far better job at generating Rust code compared to C code.
As for typing speed, I never found this to be the limiting factor. Thinking, reasoning, understanding, problem-solving; those are the actual bottlenecks.
Wow. A very nice read. Trying it all back to CFD, Fortran, and my engineering days. Much appreciated.
