<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: simplencomplex</title><link>https://news.ycombinator.com/user?id=simplencomplex</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 05 Sep 2026 07:24:13 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=simplencomplex" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by simplencomplex in "AI language models are struggling to “get” math"]]></title><description><![CDATA[
<p>Why instead of expecting a language to get math, don't we use the language model to generate code, run the code and use the result?<p>If a language model basically is the equivalent of a dumb human, how can we expect it to be better than us at math?Most humans use calculators even for simple equations.<p>I've been thinking about giving access to a search engine and a command line to a GPT-3 based AI, so that it can choose to run code it wrote or to expand its knowledge, I think that's a good way to expand its capabilities, even if that's probably how we're going to get skynet in the end.</p>
]]></description><pubDate>Thu, 13 Oct 2022 10:05:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=33189182</link><dc:creator>simplencomplex</dc:creator><comments>https://news.ycombinator.com/item?id=33189182</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33189182</guid></item></channel></rss>