The other day I reviewed a PR for one of my projects that was vibe-coded. The PR comprised a single commit with a small fix and lots of additional tests. The single commit means there’s no (easy) way to really make sure all those new tests would fail without the fix.
I think it would have been better to have the agent first write failing tests, commit that, then work on the fix and commit it separately. While I don’t vibe-code myself, I think following a strict TDD methodology can make a big difference in this respect.
Typing this comment plus a link to that pr into any coding agent hooked up to any LLM from the past couple of years would have gotten you the desired effect. ;P
The other day I reviewed a PR for one of my projects that was vibe-coded. The PR comprised a single commit with a small fix and lots of additional tests. The single commit means there’s no (easy) way to really make sure all those new tests would fail without the fix.
I think it would have been better to have the agent first write failing tests, commit that, then work on the fix and commit it separately. While I don’t vibe-code myself, I think following a strict TDD methodology can make a big difference in this respect.
score 1 · canonical
Typing this comment plus a link to that pr into any coding agent hooked up to any LLM from the past couple of years would have gotten you the desired effect. ;P
score 1 · canonical
I wouldn’t want to commit a failing test. What I have adopted from the CUE people is writing a test that asserts the broken state and then change it in the second commit.
score 1 · canonical