On: TensorKart: self-driving MarioKart with TensorFlow

[ska]

How did we get from "bare minimum sensible testing" to "This is very awesome!"? Are things that bad on average?

[kevinwang → ska]

There's probably a broad range of people in the hn community.

[ska → kevinwang]

Fair point.

NB: generalization should be one of, if not the first thing you think about and plan for in any ML project.