Re:GitHub Copilot Coding Agent
by r0ckarong on Monday May 19, 2025 @12:40PM
(#44031649)
Check in unreviewed slop straight into the codebase. Awesome.
[ Parent
| on HN ]
Copilot pushes its work to a branch and creates a pull request, and then it's up to you to review its work, approve and merge.
Copilot literally can't push directly to the default branch - we don't give it the ability to do that - precisely because we believe that all AI-generated code (just like human generated code) should be carefully reviewed before it goes to production.
(Source: I'm the product lead for Copilot coding agent.)
> Once Copilot is done, it’ll tag you for review. You can ask Copilot to make changes by leaving comments in the pull request.
To me, this reads like it'll be a good junior and open up a PR with its changes, letting you (the issue author) review and merge. Of course, you can just hit "merge" without looking at the changes, but then it's kinda on you when unreviewed stuff ends up in main.
Re:GitHub Copilot Coding Agent
by DeepYogurt on Monday May 19, 2025 @12:56PM
(#44031857)
Management: "Why aren't you going faster now that the AI generates all the code and we fired half the dev team?"
A good junior has strong communication skills, humility, asks many good questions, has imagination, and a tremendous amount of human potential.
Has a point of view, a clear motive, ability to think holistically about things that are hard to digitize, get mad and clean up a bunch of stuff absolutely correctly because they're finally just "sick of all of this shit", or, conservatively isolates legacy code, studying it and creating buffering wrappers for the new system in pieces as the legacy issues are mitigated with a long term strategy. Each move is discussed with their peers. etc etc etc thank you for advocating sanity!
I'm waiting for the first unicorn that uses just vibe coding.
Re:GitHub Copilot Coding Agent
by erikerikson on Monday May 19, 2025 @01:07PM
(#44032004)
I expect it to be a security nightmare
Re:GitHub Copilot Coding Agent
by freeone3000 on Monday May 19, 2025 @02:10PM
(#44032856)
And why would that matter?
Now developers can produce 20x the slop and refactor at 5x speed.
In my experience in VSCode, Claude 3.7 produced more unsolicited slop, whereas GPT-4.1 didn't. Claude aggressively paid attention to type compatibility. Each model would have its strengths.