<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: cluelesssness</title><link>https://news.ycombinator.com/user?id=cluelesssness</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 16 Apr 2026 01:17:07 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=cluelesssness" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by cluelesssness in "Watching o3 guess a photo's location is surreal, dystopian and entertaining"]]></title><description><![CDATA[
<p>there is also some more systematic research on this phenomenon from roughly half a year ago, demonstrating that even much less recent vision-language models are pretty good at guessing not just location but also other personal infos about you such as sex, age, education, etc.<p><a href="https://arxiv.org/pdf/2404.10618" rel="nofollow">https://arxiv.org/pdf/2404.10618</a><p>would be interesting to see how much better these reasoning models would be on the benchmark</p>
]]></description><pubDate>Sat, 26 Apr 2025 19:03:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=43806220</link><dc:creator>cluelesssness</dc:creator><comments>https://news.ycombinator.com/item?id=43806220</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43806220</guid></item></channel></rss>