review: confident-wrong pass — judge the change as a whole, not just its lines#38
Merged
Conversation
… just its lines The rubric + prompt were entirely line-level and corpus-citable (bug / type-lie / dead-code / footgun / reinvents-primitive / local over-abstraction), and the precision rule drops anything not tied to a primitive or a provable defect. So confident-wrong slop — wrong premise, overbuilt approach, hollow no-op — sailed through: no single bad line, and a polished diff actively bought a pass. Add a holistic FIRST pass that attacks the change itself (does it need to exist? simplest at the right owner? does it do what it claims?), hyper-skeptical of confident code, EXEMPT from the line-level suppression; plus three rubric kinds (wrong-premise / overbuilt / confident-noop) flaggable on confidence without a citation. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
![exe-dev-github-integration[bot]](https://avatars.githubusercontent.com/in/3061187?s=60&v=4){kind=small}
stupify (PR #38) caught the contract gap: the new whole-change kinds are exempt from corpus citation, but the comment format still required every fix line to end with (<reference file>) — forcing an invented citation or a broken output shape. Make the parenthetical conditional: keep it for corpus-cited findings, omit it for overbuilt / wrong-premise / confident-noop. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The rubric + prompt were entirely line-level and corpus-citable (bug / type-lie / dead-code / footgun / reinvents-primitive / local over-abstraction), and the precision rule drops anything not tied to a primitive or a provable defect. So confident-wrong slop — wrong premise, overbuilt approach, a hollow no-op — sailed through: no single bad line, and a polished diff actively bought a pass.
This adds:
wrong-premise/overbuilt/confident-noop, flaggable on confidence without a corpus citation.Already live on the bevyl.ai + bunion review VMs (copied to each
~/.stupify/.review/); this PR lands the source.🤖 Generated with Claude Code