This is example content for verifying the blog. It describes the publishing workflow, not the results of a completed experiment.
Start with a question
A useful experiment starts with something specific to find out. Write down the question, the setup, and what would count as a useful result before changing settings.
This notebook keeps articles as Markdown files. The site is built ahead of time, so reading a finished article does not require a model, a database, or a JavaScript server.
Keep the details
When writing up a test, include the software versions, hardware, prompts, and configuration. Separate what you observed from what you think explains it.
# Example article metadata
title: A question worth testing
draft: true
tags: [Local AI]
Show the trade-offs
Results become more useful when readers can see what failed, what changed between attempts, and the limits of the setup. A table can summarize the things you measured:
| Item | What to record |
|---|---|
| Hardware | CPU, GPU, and available memory |
| Software | Model name, release, and configuration |
| Method | Inputs, repetitions, and evaluation criteria |
| Outcome | Observations and supporting material |
Publish the finding
Change the draft flag when the article is ready. A build validates the Markdown, generates the pages, and packages the result for the server.
For an actual experiment, replace this example with your own measured findings and supporting material.