[kazinator]

> destroys readability and the ability to understand a codebase.

Aha! That's exactly the sort of thing that can make code impervious to LLM AI.

LLMs have no grasp of any issues that are not visible in syntax, like concurrency. Code that has deadlocks or race conditions (because of other code not seen elsewhere) can look right, but be wrong.

In other words, if you write a program using convoluted spaghetti logic full of invisible data members and control flows injected remotely by aspects, LLMs trained on the code will have no understanding of it; they will just predict tokens according to the naive, visible code.

Imagine if all code out there available for training LLMs was heavily AOP. LLMs trained on it wouldn't be worth a damn. They would not correctly crib the entire solution: generate the code, and bring in the invisible aspects needed to actually make it work. All their solutions would just be the naive surface code that must be invisibly instrumented by half a dozen aspects to be complete.

AOP-heavy code would have to be somehow cleverly preprocessed for training in order for token prediction to do meaningful things with it.

[Zababa]

This is not true, LLM can write and run code to check for deadlocks or race conditions.

[kazinator]

Generating code on the topic of deadlocks and race conditions is different from understanding those issues and recognizing them in a wide variety of contexts.

[Zababa]

I don't know about understanding but Claude and GPT can "recognize" lots of race conditions/possible deadlocks and then run Go with the race detector to figure out if they really happen (actually not all the time they tend to be overconfident that things are race conditions without testing first!).

I don't really know what to call that, if it's understanding, recognition, but it's clearly helping reduce the number of race condtions.