This site is generally updated on a Friday with the following Sunday’s bible readings from the lectionary.
Code scrapes the details of the readings for the Sunday, then for each reading that is found it first checks whether there’s a blog post about it. If there is, it does nothing, otherwise the fun starts.
OpenAI have been training LLMs (Large Language Models) which are mathematical models that try to represent how natural language is structured. These have been trained on vast swathes of data to try to understand and model the patterns and relationships between words, that are then transformed into probabilities.
There’s no “intelligence” as such, but if you give one of these LLMs a prompt (just a sentence in plain English), it will word by word (well, technically it works on tokens… one token is generally around three quarters of a word) try to work out what the most likely next word should be.
And so, for each of the readings we’ve got, we ask it to generate a visualisation and a limerick. We ask it to provide action points based on that passage. We ask it to provide list of related bible passages. At no point does it actually understand what we’re asking – it’s just looking at the probabilities based on our input, and generating an output based on its training data. So please don’t take this at face value. Question its output.
Each question we ask and each answer we receive costs money (roughly $0.02 per 1000 tokens).
Read about the thought process behind this site
If you’d like us to generate specific bible passages, or ask different questions, please drop us a message