Risk Assessment of GitHub Copilot

Re:Risk Assessment of GitHub Copilot by jpeloquin on Monday July 12, 2021 @02:14PM (#27813299)

Maybe Copilot could be turned into a context-aware search engine? That is, invoking it would return a list of examples that it thinks do the same thing as what you're trying to do, based on your work-in-progress code.

[ Parent | on HN ]

Re:Risk Assessment of GitHub Copilot by visarga on Monday July 12, 2021 @02:17PM (#27813323)

Seems like humans are more creative when they can get inspiration from language models.

https://arxiv.org/abs/2107.04007

[ Parent | on HN ]

Re:Risk Assessment of GitHub Copilot by bshanks on Monday July 12, 2021 @07:42PM (#27816368)

Ironic if AIs end up being more useful for creativity than for detail-oriented tasks.

[ Parent | on HN ]

Re:Risk Assessment of GitHub Copilot by jessmartin on Monday July 12, 2021 @09:46PM (#27816938)

I honestly think this is where things are going. Man-machine partnership on creative tasks. Not only is it more amenable to current models, it’s higher leverage and less likely to be completely automated away.

I wrote a little about this shift to what I think of as “conversational programming”: https://jessmart.in/articles/copilot

[ Parent | on HN ]

Re:Risk Assessment of GitHub Copilot by atatatat on Tuesday July 13, 2021 @07:15PM (#27827384)

You're not going to get it out of a generation of people raised by tablets, needs to come from somewhere.

[ Parent | on HN ]

Re:Risk Assessment of GitHub Copilot by stormbrew on Monday July 12, 2021 @08:04PM (#27816462)

This would be way more interesting of a product than what copilot actually is.

[ Parent | on HN ]

Re:Risk Assessment of GitHub Copilot by saurik on Monday July 12, 2021 @09:23PM (#27816839)

Yeah: I would love this; I actually often try to use GitHub like this, and it sort of works at times, except GitHub's search features frankly suck.

[ Parent | on HN ]