New GitHub Copilot Research Finds 'Downward Pressure on Code Quality'

3 years ago by walter_wiggles to c/programming

'We find disconcerting trends for maintainability.'

Interesting to see the benefits and drawbacks called out.

uthredii 39 points 3 years ago

In this regard, AI-generated code resembles an itinerant contributor, prone to violate the DRY-ness [don't repeat yourself] of the repos visited.

So I guess previously people might first look inside their repo's for examples of code they want to make, if they find and example they might import it instead of copy and pasting.

When using LLM generated code they (and the LLM) won't be checking their repo for existing code so it ends up being a copy pasta soup.

save

path: 0 7072717, hotness: undefined, score: 39, children: 11

sentient_loom 22 points 3 years ago

If you use AI to generate code, that should always be the first draft. You still have to edit it to make sure it's good.

save

path: 0 7072717 7073554, hotness: undefined, score: 22, children: 10

walter_wiggles 15 points 3 years ago

I totally agree, but I don't hear any discussion about how to incentivize developers to do it.

If AI makes creating new code disproportionately easy, then I think DRY and refactoring will fall by the wayside.

save

path: 0 7072717 7073554 7074141, hotness: undefined, score: 15, children: 8

hikaru755 8 points 3 years ago

Yeah, but by generating with AI you're incentivized to skip that initial research stage into your own code base, leading you to completely miss opportunities for consolidation or reuse

save

path: 0 7072717 7073554 7098922, hotness: undefined, score: 8, children: 0

Rules

Wormhole

Follow the wormhole through a path of communities !webdev@programming.dev

Rules

Wormhole

Follow the wormhole through a path of communities !webdev@programming.dev