Hacker Newsnew | past | comments | ask | show | jobs | submit | conzept's commentslogin

"But again, what's the alternative?" Blockhain based social networks would seem the obvious choice. The onramp needs to be easier I feel though. Make the ID-management, posting and global searching easy enough.


Project links:

- https://conze.pt/guide/user_manual (documentation)

- https://x.com/conzept__ (development news)

- https://github.com/waldenn/conzept (source repo)


A free topic-exploration tool based on Wikipedia, Wikidata, Archive.org, OpenAlex and other datasources. AI-based search and chat are also supported now (enter a locally stored OpenAI key).


An opensource, semantic topic exploration system, which can use any remote REST datasources (and soon self-hosted, custom TypeSense datasources).

See: https://conze.pt - this is an encyclopedic showcase, but could be used for any other information system, eg. a cultural archive.

Development news: https://x.com/conzept__

Docs: https://conze.pt/guide/user_manual

Feedback welcome! I'm aware that the mobile experience needs work.


Not true: Wikidata, Open Alex, Europeana, ... and many smaller projects making use of all that data, such as my project Conzept (https://conze.pt)


I think the future holds a synthesis of LLM functions with semantic entities and logic from knowledge graphs (this is called "neuro-symbolic AI"), so each topic/object can have a clear context, upon which you can start prompting the AI for the preferred action/intention.

Already implemented in part on my Conzept Encyclopedia project (using OpenAI): https://conze.pt/explore/%22Neuro-symbolic%20AI%22?l=en&ds=r...

Something like this is much easier done using the semantic web (3D interactive occurence map for an organism): https://conze.pt/explore/Trogon?l=en&ds=reference&t=link&bat...

On Conzept one or more bookmarks you create, can be used in various LLM functions. One of the next steps is to integrate a local WebGPU-based frontend LLM, and see what 'free' prompting can unlock.

JSON-LD is also created dynamically for each topic, based on Wikidata data, to set the page metadata.


Cool! Could you please allow for searching by URL parameter. Then I can link it from the video section on topics at https://conze.pt Thanks!


Encarta was a big inspiration for my Conzept project (https://conze.pt) - a topic exploration system based on Wikipedia, Wikidata and other (pluggable) datasources.

See many usage examples here: https://twitter.com/conzept__


Does it pick a random topic for each visitor?

Mine was 2 Girls 1 Cup o_O


The data is not licensed as opensource (only non-commercial use): "The Service and its entire contents, features and functionality (including but not limited to all information, software, text, displays, images, video and audio, and the design, selection and arrangement thereof), are owned by the Company, its licensors or other providers of such material and are protected by United States and international copyright, trademark, patent, trade secret and other intellectual property or proprietary rights laws. You are permitted to use the Service for Your personal, non-commercial use, or legitimate business purposes related to Your role as a customer of BigPicture.io." - https://bigpicture.io/terms


Not quite the same, but I've been working on geo-timeline views of Wikidata events.

WWII example: https://conze.pt/explore/World%20War%20II?l=en&t=link-split&...

Works of Rembrandt (by inception date and their location): https://conze.pt/explore/Rembrandt?l=en&t=link-split&i=Q5598...

Showing cultural periods is still to be worked out, but already supported somewhat: https://conze.pt/explore/Victorian%20era?l=en&t=link-split&i...


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: