Markdown: An effective tool for LLM interaction (relston.github.io)

See also: https://news.ycombinator.com/item?id=40866228

I think Ryan Elston's blog post is more effective in explaining the advantages of markdown for LLM interaction.

I wonder if the CLI could have a "watch mode" 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 "chat" format.

A couple of notes on the blog post: the example

echo "Please explain this code: $(cat some_class.py)" | mark

needs a dash at the end to work correctly. Also, it doesn't output pandoc-flavored markdown (blank lines before headings and code chunks) unless I specifically ask it to, as in:

echo "Please explain this code, using pandoc-flavored markdown, leaving a blank line before headings and code chunks: $(cat some_class.py)" | mark -

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

Fabric and this!!! This is promising to build on.

danielmiessler.com/p/fabric-origin-story

together with obsidian is my setup I am trying to build now. I'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: https://tildegit.org/unworriedsafari/mill.py

This looks very good, I was just reading the code on GitHub.

I mostly use local models. I might modify 'mark' myself, or wait a while and see if anyone does a pull request.

A little off topic, but I run ollama at the command line using:

echo "what is 1 + 3?" | ollama run llama3:latest