<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: ignat_244639</title><link>https://news.ycombinator.com/user?id=ignat_244639</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 01 May 2026 19:09:05 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=ignat_244639" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by ignat_244639 in "Show HN: Semantic Calculator (king-man+woman=?)"]]></title><description><![CDATA[
<p>Huh, that's strange, I wanted to check whether your embeddings have biases, but I cannot use "white" word at all. So I cannot get answer to "man - white + black = ?".<p>But if I assume the biased answer and rearrange the operands, I get "man - criminal + black = white". Which clearly shows, how biased your embeddings are!<p>Funny thing, fixing biases and ways to circumvent the fixes (while keeping good UX) might be much challenging task :)</p>
]]></description><pubDate>Thu, 15 May 2025 10:46:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=43993647</link><dc:creator>ignat_244639</dc:creator><comments>https://news.ycombinator.com/item?id=43993647</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43993647</guid></item></channel></rss>