You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: ace-fca.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,11 +1,11 @@
1
1
**PRE RELEASE** - if you're reading this, this post has not been published fully yet - feedback welcome but please don't pass this around just yet!
2
2
3
-
# Putting AI to Work in Complex Codebases
3
+
# Getting AI to Work in Complex Codebases
4
4
5
5
It seems pretty well-accepted that AI coding tools struggle with real production codebases. The [Stanford study on AI's impact on developer productivity](https://www.youtube.com/watch?v=tbDDYKRFjhk) found:
6
6
7
7
1. A lot of the "extra code" shipped by AI tools ends up just reworking the slop that was shipped last week.
8
-
2. Coding agents are great for new projects or small changes, but in large established codebases, AI can often make developers *less* productive.
8
+
2. Coding agents are great for new projects or small changes, but in large established codebases, they can often make developers *less* productive.
9
9
10
10
The common response is somewhere between the pessimist "this will never work" and the more measured "maybe someday when there are smarter models."
0 commit comments