Humans get frustrated, bored and have very limited attention. LLM cognition is almost too cheap to meter and can parallelize very effectively on both the code itself and the kind of vulnerabilities its looking for.
A bad codebase usually has more code and more bugs of common varieties. This requires a higher ability to read a lot, with lower depth of understanding.
Why would a bad codebase give AIs an advantage over humans?
Humans get frustrated, bored and have very limited attention. LLM cognition is almost too cheap to meter and can parallelize very effectively on both the code itself and the kind of vulnerabilities its looking for.
A bad codebase usually has more code and more bugs of common varieties. This requires a higher ability to read a lot, with lower depth of understanding.