Hacker News Reader

On the negative side, the code may not work.

But on the positive side, no dependencies.

How many dependencies do you review the source code of?

The expectation is that someone has already done that with a dependency. If the code has just been sharted out by an LLM, it has by definition been reviewed or even understood by no one.

There is nothing about a LLM 'sharting out code' that blocks it being reviewed or understood by a human.

What good would that do me? Levenshtein distance is one of those things that's trivial on the surface, but I have no idea if there are tricky edge conditions.

I do one better: I pull from a trusted creator or I review things like GitHub issues to ensure better people than me have reviewed it.

Or put the dependency in the unit tests so it's not part of the code base but able to be compared to the canonical implementation.