Revision Prompting: Diff your inputs for consistency and efficiency
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
Revision Prompting proposes a way to update LLM outputs after their inputs change: instead of re-running the full instruction, the model receives the original input, original output, and an input diff, and returns only an output patch.