> Agent code can only be read and understood by agents.
This just fundamentally isn't true and if this is your perspective then you're using LLMs wrong.
> Agent code can only be read and understood by agents.
This just fundamentally isn't true and if this is your perspective then you're using LLMs wrong.
Fundamentally, the code can be understood by humans, but the volume of the generated code outpaces human capacity to understand it.