Nodal point of thought 2024-05-01
2024-05-01
System for one book
Try it in the Plurality book
temporal context.
The Intellectual Production of Engineers
The Japanese version cannot be published as is.
There is an English version.
System for one Scrapbox
Try this Scrapbox
There is no temporal context in terms of the one-dimensionality of the book.
Writing is one-dimensional
There is a temporal context of proximity of creation and update dates and times.
Only if it's written by one author.
Some contexts are connected by links.
System for multiple books
Fun to discover links between different authors' descriptions
We have data.
Cannot be made public.
No, wait, there's a way: Gutenberg.
Multi-person Scrapbox projects
If you are co-editing
When referring to a link
Fractal Summary
Assuming a one-dimensional structure.
If you ignore cost, you can do a fractal summary of a single book.
I hope you understand the structure of the chapters and headings, though.
As for Plurality books and your own books, you can add metadata manually.
/blu3mo-public/Fractal Summarizer feedback summary.
2024/4/24
I was just doing something else and it occurred to me that if the terminal input is "people's diverse opinions", it could be considered a form of broad listening.
Right now it's chunking based on the order of input, so if you input a variety of opinions in different orders, you're going to get a fractal summary that you don't understand.blu3mo.icon
I was imagining it as an embedded vector and clustering it with different k's using the k-means method.nishio.icon
I see blu3mo.icon*2.
If we can chunk based on meaning rather than order, we can generate summaries that help us understand the diversity of opinions.
nishio.icon
2024-05-01
KJ method collects related labels and then bundles them together with a nameplate
This can be seen as a summary
KJ legal effect of repeatedly applying summaries.
from Current impressions and thoughts on OMNI
'Related' can be 'Scrapbox links' or 'vector similarity.'
Now that's just the "back and forth" one-dimensional fractal summary.
Where to cut a one-dimensional series of graphs
Currently, I think the size (number of pieces) is determined first, and then the pieces are cut.
Vector Search in Nishio also determines the number of tokens and cuts them by that number.
Commonly used rustic methods
I'd better see what it means and chop it up.
MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation
I'm also thinking it would be interesting to create something that bridges national languages in Japan, Korea, and Taiwan with Face the Ocean, but it doesn't seem to improve my intellectual productivity.
The multilingual glossary in the Plurality book is also a hassle when I think about the hassle of connecting to the original website.
---
This page is auto-translated from /nishio/思考の結節点2024-05-01 using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I'm very happy to spread my thought to non-Japanese readers.