We conducted an experiment to increase the number of data to be searched for in Extending the Red Link with AI, which we have been running publicly on this Scrapbox.
- Searches include other peopleās Scrapbox data, books and papers
- Since there might be some problems with publishing the generated results as they are without review, the output destination is a private project that is not open to the public.
- Subsequent updates changed the search hits to output directly to Scrapbox, making it clearly unpublishable.
- The page is automatically generated by AI at the destination of the red link created like this
mounting
- Load from local pickle
- It takes about 5 seconds to read 100,000 records
- About 7 seconds to perform a local vector search
- Itās slow when you think of it as a web app response, but with the recent āthrow a keyword or page that comes to mind, work on something else, and look at it after a whileā style, itās not a problem.
- Thereās about 10-25 minutes between when you throw the query and when I come back to check the results (I donāt measure it).
- Iāve been updating every 10 minutes to begin with, and I havenāt seen a problem.
impressions
- Do we really want to do it with āall dataā or āall except this project
/nishio
ā?- Generated using the keyword Combining knowledge is the source of new ideas, which in turn generates further knowledge and new combinations, which I already did in this project in my first experiment, I excluded it because it was not interesting because it hit almost all the pages of my project.
- titles:
["š¤š successful intelligence", "š¤š successful intelligence", "š¤š twist", "Hatena2015-01-07", "šCollaboration with AI", "Increase personal productivity first", "šsuccessful intelligence", "tkgshn/ Karabiner not working on macOS Monterey"]
- Maybe the last one is random.
- titles:
- It may be possible to find unexpected connections by not excluding my own writing, but since I am the one who makes the query, it may be true that it will be more similar to what I have written.
- I wonder if people find value in āLetting my data-derived AI live in my wikiā because it gives them a ādifferent perspectiveā.
- Not sure why I see the value of different perspectives in my own search from my own Scrapbox.
- Is it really A?ā in response to āIt is Aā. or maybe the same individual has a sufficiently varied point of view due to the accumulation of more than 10 years of experience including Hatena Diary, or maybe I am highly sensitive to read differences by thinking ā[Similarity ā What is the difference?
- Generated using the keyword Combining knowledge is the source of new ideas, which in turn generates further knowledge and new combinations, which I already did in this project in my first experiment, I excluded it because it was not interesting because it hit almost all the pages of my project.
- If you exclude yourself, it looks like this (long story, so I cut out some unnecessary details)
- titles:
["motoso/discussion"], "tkgshn/knowledge and wisdom"], "nishio-books/MOT knowledge creation management and innovation Ikujiro Nonaka"], "tkgshn/knowledge tightly coupled with business"], "mtane0412/suggestion through ignorance"], "nishio- books/idea generation method and cooperative work support Jun Munemori", "tkgshn/knowledge", "nishio-llm2023/Study of methods and systems to support knowledge creation process", "blu3mo_filtered/dualism of knowledge and ability", "motoso/wise company", "blu 3mo_filtered/accounting systems", "tkgshn/vaccine against false information", "motoso/Think different"]
- Itās interesting that the sources are pretty disparate.
- But this variance makes the current prompt less interesting to say.
-
Notebooks and ā¦ fragments are related in that the combination and exchange of knowledge generates new knowledge and ideas.
- Iām mentioning three of them, not all of them, so it would be more interesting if you talked about how they relate to each other individually.
- Iāve already tried an improved prompt in nues implementation of this, so Iāll be importing it back in the future.
-
- titles:
- Later, I tried other styles, such as having multiple lines of text commented on instead of a single line of title, but the search results themselves are more interesting than the generated text
- Itās not that the generated sentences are not interesting, itās simply interesting to see the results of the vector search
- If the interestingness of the generated results when done with my projectās data is 100, the interestingness in this experiment is 90, and the vector search results are about 300
- Iām writing a summary of todayās experiment first, holding back the urge to write about each of them individually.
- I think the individual stories are overly detailed.
- Well, if you can just imagine the book part as āa system where books pop up and related pages open when you talk about them in front of a bookshelf,ā you can understand how interesting it would be.
- In the case of Scrapbox, the other person is still alive (and books can be alive, too, of course), so there is a possibility that the connection found by the AI here could lead to more conversation with that person afterwards.
- So, the vector search results that were only output to the console are now written to Scrapbox as well.
- This naturally led to parts of books and such being written in Scrapbox, making it impossible to publish directly.
- Well, if we were originally going to do something like this, it was within the realm of possibility that we wouldnāt be able to do it in a public forum, so that was the default. - Eventually, you wonāt be able to see it.
- The question of whether to include this part of the search results in the AIās search is a difficult one.
- Effect of increasing number of fragments related to interests
- The effect of interferences between fragments of search results for the same keywords that happen to be next to each other, creating new ones.
- Adverse effects of miscellaneous machine-generated data returning to input
- Include them in the list once, and make a mechanism to mechanically remove them all together when you think itās a bad idea.
- 2023-10-05 I think itās not good, the mismatch between the title and the content is confusing
summary
- Just a casual post on a private project with a smartphone or something, and you can now see the results of vector searches across multiple peopleās Scrapbox projects, books and papers.
- We will improve it as we use it in the future.
- It would be interesting to take not only the explicitly triggered ones, but also the ones taken from the recent updates of your project once a day or so, and generate them on your own.
This page is auto-translated from /nishio/ęØŖęććÆćć«ę¤ē“¢å®éØć”ć¢2023-09-20 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. Iām very happy to spread my thought to non-Japanese readers.