T3-R6 in five minutes
A diff shows the lines you changed.
Score the old and the new on the same set.
Keep both outputs.
A prettier sentence that fails the refusal test is a regression.
Write the reason for the change in one line.
The reason line stops you from collecting prompt variants you cannot explain. If you cannot say why the line changed, revert it.
Sources and go deeper
- Brown and co-authors, Language Models are Few-Shot Learners, 2020 paper last checked 2026-10
- Prompt engineering — Wikipedia wikipedia last checked 2026-10