generative-ai: Add anti pattern example (gh-1679)

* generative-ai: Add anti pattern example

* reformat

* Address code review

* Add one more case

* reformat

* Address code review

* fix

* Update heading and use sentence case

Co-authored-by: Ned Batchelder <[email protected]>

* Improve wording and spacing for principles

Co-authored-by: Hugo van Kemenade <[email protected]>

* Apply suggestions from code review

Co-authored-by: Carol Willing <[email protected]>

---------

Co-authored-by: Carol Willing <[email protected]>
Co-authored-by: Ned Batchelder <[email protected]>
Co-authored-by: Hugo van Kemenade <[email protected]>

Author: 4 people

getting-started/generative-ai.rst

@@ -4,10 +4,10 @@
 Generative AI
 =============
 
-Generative AI has evolved rapidly over the past decade and will continue in the future.
-Using generative AI and large language models (LLMs) can be helpful tools for contributors.
-Their overuse can also be problematic, such as generation of incorrect code, inaccurate documentation, and unneeded code churn.
-Discretion, good judgement, and critical thinking **must** be used when opening issues and pull requests.
+Generative AI tools have evolved rapidly, and their suggested results can be helpful. As with using any tool, the resulting contribution is
+the responsibility of the contributor. We value good code, concise accurate documentation, and avoiding unneeded code
+churn. Discretion, good judgment, and critical thinking are the foundation of all good contributions, regardless of the
+tools used in their creation.
 
 Acceptable uses
 ===============
@@ -24,3 +24,17 @@ Unacceptable uses
 Maintainers may close issues and PRs that are not useful or productive, including
 those that are fully generated by AI. If a contributor repeatedly opens unproductive
 issues or PRs, they may be blocked.
+
+Considerations for success
+==========================
+- While AI assisted tools such as autocompletion can enhance productivity, they sometimes rewrite entire code blocks instead of making small, focused edits.
+  This can make it more difficult to review changes and to fully understand both the original intent of the code and the rationale behind the new modifications.
+  Maintaining consistency with the original code helps preserve clarity, traceability, and meaningful reviews and also helps us avoid unnecessary code churn.
+- Sometimes AI assisted tools make failing unit tests pass by altering or bypassing the tests rather than addressing the underlying problem in the code.
+  Such changes do not represent a real fix. Authors must review the work done by AI tooling in detail to ensure it actually makes sense before proposing it as a PR.
+- Keep the following principles for the quality of your contributions in mind whether you use generative AI or not:
+
+  - Consider whether the change is necessary
+  - Make minimal, focused changes
+  - Follow existing coding style and patterns
+  - Write tests that exercise the change