Generated Code Generates Overconfident Coders: https://www.deeplearning.ai/the-batch/issue-180/
A study of programmers found that using a LLM for completion produced buggier code but users were more confident in it.
I wonder if this generalises to other completion techniques?
miniblog.
Related Posts
I've seen atom described as 'a text editor for coders'. That is comically broad. It's hard to think of an editor that isn't for coders.
