If you could get an LLM to write the article, why not just get it to rewrite the code?
I'm not sure how feasible that would have been three years ago.
Good luck doing that without proper tests - I assume finance stuff is quite complicated and blanked porting with AI is insanely difficult, especially companies have failed in porting it by hand.
An Agent Team of Opus 4.6 should be able to reverse engineer the simulator in a day or two, instead of 3 years. But it wouldnt be so much fun I guess.