Markdown: An effective tool for LLM interaction

A couple of notes on the blog post: the example<p>echo &quot;Please explain this code: $(cat some_class.py)&quot; | mark<p>needs a dash at the end to work correctly. Also, it doesn&#x27;t output pandoc-flavored markdown (blank lines before headings and code chunks) unless I specifically ask it to, as in:<p>echo &quot;Please explain this code, using pandoc-flavored markdown, leaving a blank line before headings and code chunks: $(cat some_class.py)&quot; | mark -

This looks very good, I was just reading the code on GitHub.<p>I mostly use local models. I might modify &#x27;mark&#x27; myself, or wait a while and see if anyone does a pull request.<p>A little off topic, but I run ollama at the command line using:<p>echo &quot;what is 1 + 3?&quot; | ollama run llama3:latest

I wonder if the CLI could have a &quot;watch mode&quot; where it watches a file or directory, and automatically append the response as you edit and save a Markdown file. Not sure how well it would work in practice, but seems like it could be an interesting alternative to the &quot;chat&quot; format.

Fabric and this!!! This is promising to build on.<p>danielmiessler.com&#x2F;p&#x2F;fabric-origin-story<p>together with obsidian is my setup I am trying to build now. I&#x27;m using obsidian to plan the vector and meta data to pull and reference with the assistants and building function tools to query.

A similar tool for llama.cpp: <a href="https:&#x2F;&#x2F;tildegit.org&#x2F;unworriedsafari&#x2F;mill.py" rel="nofollow">https:&#x2F;&#x2F;tildegit.org&#x2F;unworriedsafari&#x2F;mill.py</a>

This looks cool. It would ve great, if this would get integrated into a Obsidian plugin

See also: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=40866228">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=40866228</a><p>I think Ryan Elston&#x27;s blog post is more effective in explaining the advantages of markdown for LLM interaction.