Expose clipboard formats before debugging paste

Published by Simon Willison

This credits the original publisher. Better Loop membership or a shared assessment is not implied.

The public work

Willison built a browser clipboard viewer while investigating rich-text paste. His public write-up links the code and conversation; the conversation shows requests to display available formats and then make long output easier to inspect.

What to notice

Create a small inspection tool that reveals the actual input representation before changing the application that consumes it.

Keep the context

This is an author-documented debugging utility, not evidence of compatibility with every browser or safe handling of arbitrary pasted HTML. The tool was not executed during this research.

AI use: Documented in the source.

The author identifies Claude Artifacts as the workflow. The linked conversation documents requests and generated code; it does not identify the exact model version.

A useful public example is not an assessment of a reader, a publisher or a Better Loop member.

Authored practice suggestion

Try the idea.
Check your own work.

Use material you are allowed to work with. This suggestion is preparation; it does not record a completed task or an improvement.

A prompt to adapt privately

For a public sample containing plain text and formatted text, ask for a small inspector that displays each available representation separately. Review what is lost when formatting is removed. Keep sample data local and use the findings to describe one concrete paste-handling requirement.

A check to adapt

The inspection distinguishes plain text from formatted content, and the proposed requirement addresses an observed difference.

Open a related practice brief

Private practice needs no account. Your configured model provider may process the evidence you select.

See the full skill-to-sharing flow

Another way into the work.

Iterate on a tolerant XML parser

Ronacher published a tolerant XML parser after earlier parsing approaches failed. He describes directing the initial implementation, reviewing it, requesting further fixes and an extensive test suite, and releasing the resulting library.

Published byArmin Ronacher

Curated public exampleNotebook

Code & software

Check the expected values in generated tests

OpenAI publishes a multi-step test-writing notebook with a concrete Pig Latin function and generated pytest cases. Several printed expected values conflict with the function, making this a worked example of why generated tests themselves need review.

Published byOpenAI Cookbook

Curated public exampleCode