Pipelines and AI?

A long time ago I described pipelines and where they could go.

I was made aware of Google’s OPAL project and reminded of how strong pipelines can be for managing complexity.

The pipes are described by prompts but interestingly you can reuse and share pipes and the whole flow. Which leads me to wonder if there might be a little market place for the pipes?

Might need to keep an eye on Opal, but wondering if there are better solutions. For example Xproc which can interface with APIs of large language model without getting into the weeds?

Author: Ianforrester

Senior firestarter at BBC R&D, emergent technology expert and serial social geek event organiser. Can be found at cubicgarden@mas.to, cubicgarden@twit.social and cubicgarden@blacktwitter.io

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

To respond on your own website, enter the URL of your response which should contain a link to this post's permalink URL. Your response will then appear (possibly after moderation) on this page. Want to update or remove your response? Update or delete your post and re-enter your post's URL again. (Find out more about Webmentions.)