21–30 of 30 posts
Is this really where we've landed? I refuse to believe that any of this markdown insanity will continue indefinitely.
QUALITY.md feels similar to CONSTITUTION.md Looks like unless something better comes up, we'll be stuck with it for a while. I find markdown useful for repo-specific conventions, especially skills.
Earlier quoted context omitted.
QUALITY.md feels similar to CONSTITUTION.md Looks like unless something better comes up, we'll be stuck with it for a while. I find markdown useful for repo-specific conventions, especially skills.
> I find text useful for repo-specific conventions, especially skills.
This is perfectly encapsulated in xkcd's "Standards" strip [ https://xkcd.com/927/ ].
Earlier quoted context omitted.
> I find text useful for repo-specific conventions, especially skills.
sure, but structured text like markdown is even more useful, since humans can parse and understand it as easily as skills can
And there are a number of nice viewers / editors either already installed or easily installable on most operating systems to view / edit Markdown in a "beautified" fully rendered form, on both CLI and GUI interfaces; and since most (all these days?) LLMs also "understand" Markdown formatting pretty-much natively, you can easily emphasize certain points to add "weight" to them in the LLMs' "mind" / "thinking" (calculation of statistical token probabilities) process. Plaintext without Markdown is just ... well ... plain. :)
Is this really where we've landed? I refuse to believe that any of this markdown insanity will continue indefinitely.
it's looking like llms are interpreters, and markdown plus english text is the language of choice to run non deterministic programs on it
That's actually a pretty good clear way of putting it for the typical nerdy "programmer minded" individual.
Is this really where we've landed? I refuse to believe that any of this markdown insanity will continue indefinitely.
it is until we define real consistent deterministic gates and protocols. It really is a symptom of the lack of concerted effort. Everyone has a personal preference on how to shove the context and most of them are just "here's some good text I've found to work in my context"
I've been experimenting with doing kinda exactly that with the "routing layer" / "harness" level of things, before the "main" LLM itself ever receives the user's input, by getting "user intent" (as a little JSON packet) really quickly from an ultra-lightweight model first and deciding from there in deterministic code what "context" to inject into the user message template, which system prompt to use, and which model to route the assembled context "packet" to for the final response. These LLMs really are fun to play with once you get a feel for which ones do what well, and where each falls short so you can use them each around their individual strengths. :)
Here's the question I ask about every project that claims to make a LLMs output so much better: If it works so well then why would the model provider not just put it in the system prompt? Or in the case of interactive skills, why would Claude Code/Codex not make it a core part of the product? On top of that, if your magic markdown file really does work then where's the evidence showing that? These projects never incl…
Whats the revenue model for this NBPaaS? (No Bugs Please As A Service)
The agent skill/CLI that's provided generate a quality evaluation report with recommendations for handoff (ideal for loop engineering) is just one example of how the QUALITY.md file can be used.
It's easy to imagine a SaaS that does the same that provides better eval, reporting, and integration capabilities.
This is perfectly encapsulated in xkcd's "Standards" strip [ https://xkcd.com/927/ ].