<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: xyz7786</title><link>https://news.ycombinator.com/user?id=xyz7786</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 25 Jul 2026 05:22:37 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=xyz7786" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by xyz7786 in "AWS: Inaccurate Estimated Billing Data – $1.7 billion"]]></title><description><![CDATA[
<p>$250 billion. Nearly died right then and there</p>
]]></description><pubDate>Fri, 17 Jul 2026 13:44:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=48947347</link><dc:creator>xyz7786</dc:creator><comments>https://news.ycombinator.com/item?id=48947347</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48947347</guid></item><item><title><![CDATA[New comment by xyz7786 in "Sketch-of-Thought: Efficient LLM Reasoning"]]></title><description><![CDATA[
<p>After reading both papers, I have to disagree. Chain of Draft seems "identical" to Concise Chain-of-Thought (CCoT) <a href="https://arxiv.org/abs/2401.05618" rel="nofollow">https://arxiv.org/abs/2401.05618</a>. Additionally, the CoD authors seem to mention that it is cognitive inspired but don't give any actual basis for that.<p>Sketch-of-Thought, while similar in terms of its goal, seems to be based on cognitive science principles and has better extensibility than CoD and CCoT (they basically just say "answer in X words" and leave it at that).</p>
]]></description><pubDate>Thu, 20 Mar 2025 06:29:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=43420295</link><dc:creator>xyz7786</dc:creator><comments>https://news.ycombinator.com/item?id=43420295</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43420295</guid></item></channel></rss>