<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: airtnp</title><link>https://news.ycombinator.com/user?id=airtnp</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 12 Sep 2026 06:34:37 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=airtnp" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by airtnp in "A misalignment of AI in mathematics"]]></title><description><![CDATA[
<p>I'm so bored by HackerNews commenters on decelerationism stuff. Model doesn't care; the ability for math problems is emerging, not trained.<p>These mathematicians are not suggesting anything interesting, and the announcement more like desperate crying stuff</p>
]]></description><pubDate>Sat, 12 Sep 2026 01:05:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=49667542</link><dc:creator>airtnp</dc:creator><comments>https://news.ycombinator.com/item?id=49667542</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49667542</guid></item><item><title><![CDATA[New comment by airtnp in "How we use binary search to find compiler bugs"]]></title><description><![CDATA[
<p>JReduce (<a href="https://dl.acm.org/doi/abs/10.1145/3453483.3454091" rel="nofollow">https://dl.acm.org/doi/abs/10.1145/3453483.3454091</a>) uses similar technique but with semantics for debugging such problems with Java decompiler and bytecodes.<p>The problem is we don't know if compiling with these functions follows the monotonicity of binary searching: what if a problem is caused by a special combination of two functions? You have to arrange these two functions in the right order in order to find the problem.</p>
]]></description><pubDate>Sat, 22 Oct 2022 03:24:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=33295420</link><dc:creator>airtnp</dc:creator><comments>https://news.ycombinator.com/item?id=33295420</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33295420</guid></item><item><title><![CDATA[New comment by airtnp in "Show HN: PRQL 0.2 – a better SQL"]]></title><description><![CDATA[
<p>This sounds like LINQ, or SparkSQL. Instead of a full new language, it makes feel better to create libraries in languages that supports embedded DSL easily.</p>
]]></description><pubDate>Mon, 27 Jun 2022 19:31:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=31899611</link><dc:creator>airtnp</dc:creator><comments>https://news.ycombinator.com/item?id=31899611</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=31899611</guid></item></channel></rss>