You may have noticed I haven't posted much since July.
When Claude Fable came out, things I'd wanted to implement in LinkedDataHub for years suddenly took days. It was also the first model I trusted with platform-wide refactoring. So I spent my time building.
The agent didn't design the architecture. That came from ten years of building Linked Data and Knowledge Graph apps for different use cases, identifying what they had in common, and turning that into a domain-independent platform.
LinkedDataHub 6:
https://t.co/tOYjVPWzD9
You may have noticed I haven't posted much since July.
When Claude Fable came out, things I'd wanted to implement in LinkedDataHub for years suddenly took days. It was also the first model I trusted with platform-wide refactoring. So I spent my time building.
- Apps supply their own XSLT stylesheets, running on the server and in the browser.
- Bootstrap 2 is gone. The new design system supports light and dark modes.
- Every dataspace serves /AGENTS.md, so agents can discover how to work with it.
@bradneuberg@davewiner Hope is not lost :) Check out SaxonJS - a high-performance XSLT 3.0 processor that runs either in the browser, or on Node.js.
https://t.co/tLHtszRZMx
LinkedDataHub 6 is out.
The application is data: classes, forms, views, charts and access rules are RDF documents. You deploy an app by pushing a directory of RDF documents and the files they use, and an agent can write one.
What changed:
https://t.co/BIaY077dEs
@wohnjalker Vertically I suppose, but not horizontally across applications. You cannot merge data from arbitrary applications or cross-query it without writing one more program.
Jev's founder makes two good points.
"Data matters way more than compute." Coming from a company that sells models, that's worth paying attention to.
He also wants models to be "a new primitive, more like databases and APIs rather than facsimiles of co-workers."
Diogo Almeida (@CompleteSkeptic), AI Council, "AI: Too Good to Be True, Too Bad to Be Useful".
Data vs compute: 11:44. Models as primitives: 36:16.
https://t.co/QgLxzzcsDm
Jev separates judgement from generation, so a decision becomes a typed value instead of an instruction in a prompt.
I want the same for applications. What the data model can guarantee shouldn't have to be reimplemented in code or restated in prompts.
@pjurjac@PeculiarLi34455@dbpedia@wikidata@uniprot are running on this scale.
Graph traversal is not my use case - graph pattern matching is.
But the most value I get out of RDF is how it makes web applications generic because it’s the only web-native data model.
https://t.co/LIoe9P8u5A