Live data from Hacker News

40% of the code GitHub Copilot users check-in is AI generated and unmodified

microsoft.com

1–10 of 129 posts

Re: 40% of the code GitHub Copilot users check-in is AI generated and unmodified

#4

A lot of the code it generates is trivial, or 1-2 lines of code that's obvious, at least for me. In which case, it makes no sense to modify it. I have a feeling this is the bulk of it.

This is my experience as well. For longer code, Copilot introduces errors through making up variables and method names that don't actually exist on the object. These errors are very annoying but only 5% of the generated code.

Re: 40% of the code GitHub Copilot users check-in is AI generated and unmodified

#5
I'm not surprised. A lot of the code I'll write in a day is trivial, calling helpers, writing test scaffolding, etc. I'm still building cool things the other 60% of time, but this job as we know it comes with a lot of repetition. (esp. if you write unit tests ;-))

Re: 40% of the code GitHub Copilot users check-in is AI generated and unmodified

#7
Sure this must be using the most generous possible interpretation of the data. In my IDE the suggestion is shown as an autocomplete option on basically every keypress. I will only hit tab to insert if it is what I was planning to type. Sometimes if I really want to use it I'll coax it, write a comment or edit my code a bit to give it some help until the suggestion is what I want. There's no way they're counting every autocomplete suggestion in the denominator of that percentage.

Re: 40% of the code GitHub Copilot users check-in is AI generated and unmodified

#9

I'm not surprised. A lot of the code I'll write in a day is trivial, calling helpers, writing test scaffolding, etc. I'm still building cool things the other 60% of time, but this job as we know it comes with a lot of repetition. (esp. if you write unit tests ;-))

unit test definitely a great use of copilot.
Post reply on HN