[dead]
Google proposes Open Knowledge Format based on Markdown
11–19 of 19 posts
Re: Google proposes Open Knowledge Format based on Markdown
#12Check out barrasindustries.com/okfind/
Just an idea for an OKF bundle registry
Re: Google proposes Open Knowledge Format based on Markdown
#13I love the simplicity of this OKF spec, but I'm not sure everything can be represented well in "just Markdown". I've recently become intrigued by representing concepts so that AI can co-contribute effectively and token-efficiently (typically: find a good way to represent something as semi-structured sequential text), but also without compromising the human lens on the representation. We shouldn't accept a downgrade o…
OKF seems OK, but bound to Markdown. A Markdown document can be turned into an OKF document by adding a 'type' to the frontmatter YAML. What about a knowledge graph language, which can be stated in Markdown prose, in Markdown code blocks, but also everywhere a text field is waiting for you? In the minimalistic language https://ddot.it you can link outside the Markdown world, to files, URLs or even just labels. Like O…
I love how unobtrusive that is, great compromise between readability and expressiveness!
Re: Google proposes Open Knowledge Format based on Markdown
#14Love the approach. I am a big fun of hierarchical knowledge organization. I think that almost all current Claude abstractions to knowledge management are broken. It becomes visible when you start running many coders concurrently or need to create 1K+ skills fe: https://news.ycombinator.com/item?id=48407998
Re: Google proposes Open Knowledge Format based on Markdown
#15Having looked at many PDFs that needed to be “translated” to Markdown, it feels like a strange choice - I know it’s primarily to make things easily accessible to AI, but if we’re going to train models anyway, why not train them on something better? Markdown is quite limited, and can’t render something like a nested table for example, and if the point of having “open knowledge” is for AI, why do we need to use a format that won’t really be read by humans?
Re: Google proposes Open Knowledge Format based on Markdown
#16Earlier quoted context omitted.
OKF seems OK, but bound to Markdown. A Markdown document can be turned into an OKF document by adding a 'type' to the frontmatter YAML. What about a knowledge graph language, which can be stated in Markdown prose, in Markdown code blocks, but also everywhere a text field is waiting for you? In the minimalistic language https://ddot.it you can link outside the Markdown world, to files, URLs or even just labels. Like O…
I love how unobtrusive that is, great compromise between readability and expressiveness!
Thanks, it is based on an unreleased 50-page complex syntax speec with over 40 different kind of arrows. Luckily, I simplified BEFORE release :-)
Re: Google proposes Open Knowledge Format based on Markdown
#17Google has announced… Markdown with YAML front-matter, ladies and gentlemen. Please applause. 15kb of spec for this!
(I’d be less sardonic if we could all stop using oops-you-missed-an-indent-YAML.)
Re: Google proposes Open Knowledge Format based on Markdown
#18The way I understand it, it is essentially a scaffolding for us humans, since we can't see past 3d. Hopefully we can do a decent job so that the agents can take our markdown and build the graph infra in memory or store in neo4j.
Re: Google proposes Open Knowledge Format based on Markdown
#19I'm a massive fan of capturing domain knowledge in a plain text format that both humans and AI can use, one of my favourites being concept maps stored in human readable form. I did a talk on this exact topic long before we all got AI pilled, this version from 2015 for example:
https://www.infoq.com/presentations/concept-map/
The web app mentioned in that talk that I built to help with that no longer exists, but I recently built a new desktop app (Apple Silicon Mac only so far, sorry) for this exact purpose: https://thinkingtools.software/concepticon