Personal Timeline

from Diary 2024-08-26 Personal Timeline

When you need random stimulation to take a break.

• You should get some sleep.
• We don’t need Twitter, we need a timeline that randomly shows articles we want to read but haven’t, or long articles, or friends’ Scrapboxes, etc.
• Same as [boiled frog
  • The gradual decline in quality makes us accustomed to it.
• When you put in a large piece of content, such as a book, you should be able to chop it into chunks of reasonable length
  • And we can use LLM to extract “chunks of meaning” from it.
    • Let’s call this a tweet.
  • Put it in the DB and display it randomly.
    • You can like, bookmark and mute.
      • The difference between likes and bookmarks is currently unclear. In the past on Twitter, “likes” were public and “bookmarks” were private?
    • When you click on a tweet that interests you, the results of a vector search on that content are displayed as “related tweets”.
• I’m currently putting my Scrapbox into a vector search engine every day for vector searches, so I’m sure I can derive from that.

---

This page is auto-translated from /nishio/個人用タイムライン 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.