The most recognizable thing about AI generated code seems to be its commenting style: there's a dearth of fully-formed sentences and an abundance of "the next line of code is doing X".

[cdegroot@mstdn.ca]

The most recognizable thing about AI generated code seems to be its commenting style: there's a dearth of fully-formed sentences and an abundance of "the next line of code is doing X".

Now, my take on LLMs generating code is that they generate the mean of all code they encountered. Just as with testing, this commenting style is indicative of just how bad human-generated code seems to be, on average.

I won't stand for this reduction of quality, but I'm sure that half the coders out there will see an improvement by using AI