The worst thing is when LLMs introduce subtle bugs into code and one just can't spot them quickly. I was recently doing some Langfuse integration and used Cursor to generate skeleton code for pushing some traces/scores quickly. The generated code included one parameter "score_id" that was undocumented in Langfuse but somehow was accepted and messed the whole tracking up. Even after multiple passes of debugging I couldn't figure out what the issue with tracking was, until I asked another LLM to find any possible issues with the code, that promptly marked those score_id lines.
This is a very important lesson because the way these coding models are built. You have to understand HOW they are designed from the base LLMs. And more importantly why it’s crucial to use two distinctly different models to review each other at every turn.
