I realized that the two things I&#39;ve been doing lately can be summed up as &quot;systems that make questions better.&quot;
A: <a href="/en/Vector%20Search%20in%20Nishio">Vector Search in Nishio</a>
<ul>
<li>This is not easy to understand at first glance, so I&#39;ll explain it in context<ul>
<li>To begin with, my Scrapbox vector search was working locally.</li>
<li>There was no incentive to make it a public service.</li>
<li>I thought it would be interesting to see <a href="/en/an%20AI%20Teaching%20Assistant">an AI Teaching Assistant</a> that <a href="/en/collects%20and%20improves">collects and improves</a> questions.</li>
</ul>
</li>
</ul>
B: <a href="/en/Questioning%20by%20OpenAI">Questioning by OpenAI</a>
<ul>
<li>This polis &quot;which questions should be delved into&quot;.</li>
</ul>
<hr>
This page is auto-translated from <a href="https://scrapbox.io/nishio/%E5%95%8F%E3%81%84%E3%82%92%E8%89%AF%E3%81%8F%E3%81%99%E3%82%8B%E3%82%B7%E3%82%B9%E3%83%86%E3%83%A0">/nishio/問いを良くするシステム</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.

A system that asks better questions