In my post State of generative AI in Software Development: The reality check, I’ve mentioned a very important observation I had:
Consider the following two hypothetical situations:
1) An LLM generates 80% accurate code, where the remaining 20% inaccurate code is very difficult to debug!
2) Another LLM generates 60% accurate code, but the remaining 40% inaccurate code is very easy to debug.
If this is the case, then the second result would most likely be far more preferable to many developers!
Hence, this scenario must also be considered in judging the code generation performance of an LLM.
Today, I thought I should ask fellow developers about their opinion on this matter!
So I posted a poll on X about it!
So what do you prefer?
I’d love ♥️ to know your preference on this!