Comment by irishcoffee

Why not just try it yourself? Doing that and giving your own report would be 100x more useful than your comment or mine. I just don't care about the results.

Q: "How well can a statistical gradient descent parser that someone fucked with for a while, deceive other statistical gradient descent parsers/humans?"

A: "Deceit implies intent. Statistical gradient descent parsers are incapable of intending anything. Sometimes weights are ignored in favor of others because of how the model was fucked with. That is as close as it gets to intent."