Introduction
Artificial Intelligence (AI) is technically speaking about Machine Learning (ML), and increasingly via Artificial Neural Networks (ANNs), even though many other methods exist.
What most associate with AI today is Large Language Models (LLMs) that are trained on vast amounts of information from the web, but we are increasingly moving towards multi-modal solutions that also handle voice, pictures and videos.
Assistants
OpenAI’s Assistants API packages GPT, Dall-E and other features into one API. This seems to be the best feature moving forward to integrate with other systems as well as build UI abstractions for fixed-topic applications, whether they are prompt-, voice-, or GUI-based, including with timed or event-based automation of tasks.
I’ve used the Assistants API to e.g. create stories for children based on a basic description that sets the foundation for the stories.
Solutions
- Guppy – An OpenAI GPT client using Chat Completion and streaming
Assistants
These are based on Meow Apps AI Engine that communicates with OpenAI’s API. They all require logging in to use.
- Läkarassistent (Doctor’s Assistant)
- Storyteller
- Identifier
Tutorials
- Professional uses of ChatGPT
- Experimenting with Dall-E version 3
- Demonstrator for OpenAI Assistants API
- Getting creative with Dall-E3
Generated content
Here is content generated by OpenAI GPT and Dall-E3: