My company is all in on GitHub Copilot. They have very unrealistic expectations for how much it will increase productivity. I suspect they were sold on data from junior developers, who I think it helps the most. Anyways, now they are measuring how much engineers use it, so there is some amount of pressure to use it more often.

The training was a little worrisome and disingenuous. The internal team advocating for it aren’t strong coders and kept showing examples of it automating antipatterns, like writing useless tests that duplicate an if statement in the tested function, writing very verbose and vague comments (meaningless), or taking an example function and making a new one in a boiler plate way (that cut/pastes common code rather than extracting it into a shared function).

Really, I think it’s helpful – sometimes. Especially to new engineers or when dealing with an unfamiliar library. But I do worry it will lower the bar, and feel over using it can be a waste of time.

I’ll add that even when you’re an expert in both languages, it’s common to see WTF’s in the original and not be sure if something is a bug or just weird behavior that’s now expected. Especially when going from a looser to a more strict language.

I’ve translated huge projects and most of the risk is in “you know the original would do the wrong thing in these x circumstances – I’m pretty sure that’s not on purpose but… Maybe? Or maybe now someone depends on it being wrong like this?”

The difference is that plant identification is a classification problem, not an LLM.