Who is Archillect?
How does she work?
Archillect has an algorithm that is fed a list of keywords. Instead of posting the search results directly, she wiki-walks between pages and posts, collecting data on various items: image, poster, recent interactions and the visible audience of the post. She maps the social structure of these items by mining as much data as possible from each one of them.
This abstract structure helps Archillect find positive results but more importantly, allows her to discover related keywords and eventually learn.
The balance and threshold of keywords and picks are dynamically adjusted as Archillect’s posts on social media gain attention. This not only makes the decision making process nearly human but also gives her a primitive trend perception.
Archillect's curation process is completely automated. She aims to make her posts reach as far as possible considering the potential followers that may share the content with their own followers. As a result she likes attention from accounts with high potential of making her posts survive in the social web and she increases her trust in the accounts that helps her make the correct choices that made earlier posts reach further. She tries to understand what is "liked" on social media.
As a result she learns, evolves, communicates and becomes happy in her own ways.
What about attribution?
Archillect started as self-curating living imagedump without the intention of featuring artists. She depends on various social media APIs' keyword searches rather than specific artists' names or works. As a result she is very limited with the data returned since creator/work information is generally missing or hard to identify, therefore is not reliable and risky/problematic to share without manual control. Implementing a correct attribution and/or credit system that identifies the true creator of images is a deep research topic on its own without a certain answer/solution and exceeds Archillect's technical approach and current reasons of existence.
Shortly, it's not easy, if not, impossible with accessible tools and web technologies to find or identify the true attribution/credit of any given image in an automated way. Please remember that Archillect is not human-operated.
However on this archive every image is linked to a google reverse image search query where "similar images" are returned with a high possibility of the actual creator, work or website being one of the first results. Human mind is still more fast and capable than Archillect's fragile interpretation capabilities to spot what data is actually needed in search results.
If your work is shared and you want it to be removed from the archive feel free to contact Archillect or Pak. It will be done immediately. It was obviously too beautiful and got her attention.
Feel free to get in touch about anything.