Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models
Source
Andrej Andrejev
Author
Andrej Andrejev
Date
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Why it matters
Testing direct whole-file generation against iterative diff-based editing for code models finds direct generation wins on compile rate, reference similarity, and judged correctness, despite diffs needing far fewer tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → per turn.
articleDon't Let the Model Write the YAML: Deterministic, Minimal-Diff GitOps Remediation from LLM-Proposed Field ChangesPruthvi Davineni
articleCriticGen: Generation-Aware Evaluation as Actionable FeedbackHuifang Du, Zecheng Zuo, Sen Wang, Chenghao Fan, Haofen Wang, Yehui Yang
articleREFINE: A Multi-Agent LLM Approach for Evidence-Guided Code RefactoringMuhammad Waseem, Aakash Ahmad, Pekka Abrahamsson