from <a href="/en/Diary%202024-08-26">Diary 2024-08-26</a>
Personal Timeline
When you need random stimulation to take a break.
<ul>
<li>You should get some sleep.</li>
<li>We don&#39;t need Twitter, we need a timeline that randomly shows articles we want to read but haven&#39;t, or long articles, or friends&#39; Scrapboxes, etc.</li>
<li>Same as [boiled frog<ul>
<li>The gradual decline in quality makes us accustomed to it.</li>
</ul>
</li>
<li>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<ul>
<li>And we can use LLM to extract &quot;chunks of meaning&quot; from it.<ul>
<li>Let&#39;s call this a tweet.</li>
</ul>
</li>
<li>Put it in the DB and display it randomly.<ul>
<li>You can like, bookmark and mute.<ul>
<li>The difference between likes and bookmarks is currently unclear. In the past on Twitter, &quot;likes&quot; were public and &quot;bookmarks&quot; were private?</li>
</ul>
</li>
<li>When you click on a tweet that interests you, the results of a vector search on that content are displayed as &quot;related tweets&quot;.</li>
</ul>
</li>
</ul>
</li>
<li>I&#39;m currently putting my Scrapbox into a vector search engine every day for vector searches, so I&#39;m sure I can derive from that.</li>
</ul>
<hr>
This page is auto-translated from <a href="https://scrapbox.io/nishio/%E5%80%8B%E4%BA%BA%E7%94%A8%E3%82%BF%E3%82%A4%E3%83%A0%E3%83%A9%E3%82%A4%E3%83%B3">/nishio/個人用タイムライン</a> 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 <a href="https://twitter.com/nishio_en">@nishio_en</a>. I&#39;m very happy to spread my thought to non-Japanese readers.