[grammarxcore]

I'm not a fan of the title, which is rather clickbaity. The author addresses that in the article near the bottom.

> To be fair, I have absolutely no clue what the $86M figure includes — nor can I speak to the accuracy of my open source tool with no localized training vs. the pilot BlueNet system.

While I have no doubt that the author's solution is a cleaner approach more suited to real government than the cronyism probably involved in that 86M figure, sensationalizing the difference doesn't help FOSS government advocates. 57 lines of code also doesn't include the libraries involved, so I feel like this is just meant to grab attention. It's pretty rad, but the way it's presented doesn't lend itself to credibility and adoption.