*for some cases
Using cloud sandboxes to run them in I tested: - A single coding agent just told to make a better parser - An agent told to write a better parser within the constraints of tests/benchmarks - An agent swarm that self-improved the premise with extra tests/benchmarks in order to more "truly" write a better parser
The results were a success! I was able to end up with both performance (up to 3.07× faster) and memory (up to 5.75× less) in locally runnable benchmarks.
i mean, well done
> using direct mutual recursion instead of array-stack machinery
the reason for array-stacks is using recursion can "blow the stack" i.e. has almost arbitrary failure on deeply nested pathological inputs
using recursion is going to be faster, to about the degree you bench, but there is a reason the parser you bench against doesn't use it!