<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: madagang</title><link>https://news.ycombinator.com/user?id=madagang</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 24 Apr 2026 17:13:34 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=madagang" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by madagang in "DeepSeek v4"]]></title><description><![CDATA[
<p>Their Chinese announcement says that, based on internal employee testing, it is not as good as Opus 4.6 Thinking, but is slightly better than Opus 4.6 without Thinking enabled.</p>
]]></description><pubDate>Fri, 24 Apr 2026 04:16:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=47885447</link><dc:creator>madagang</dc:creator><comments>https://news.ycombinator.com/item?id=47885447</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47885447</guid></item><item><title><![CDATA[In the era of "Vibe Coding", when Agents are writing code – what are you doing?]]></title><description><![CDATA[
<p>In the vibe coding era, AI agents are busy generating functions, wiring tests, and filling in boilerplate.<p>I catch myself just sitting there, scrolling on my phone — and it feels like wasted time.<p>So I wonder: what’s the right human role in this loop? Higher-level design? System thinking? Critical auditing? Or are we destined to be “idle supervisors” while machines do the typing?<p>How are you using those gaps when the Agent is writing code?</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45320065">https://news.ycombinator.com/item?id=45320065</a></p>
<p>Points: 9</p>
<p># Comments: 9</p>
]]></description><pubDate>Sun, 21 Sep 2025 04:28:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=45320065</link><dc:creator>madagang</dc:creator><comments>https://news.ycombinator.com/item?id=45320065</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45320065</guid></item><item><title><![CDATA[New comment by madagang in "Open models by OpenAI"]]></title><description><![CDATA[
<p>OpenAI/Claude's company policy does not allow China to use them.</p>
]]></description><pubDate>Wed, 06 Aug 2025 03:19:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=44807241</link><dc:creator>madagang</dc:creator><comments>https://news.ycombinator.com/item?id=44807241</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44807241</guid></item></channel></rss>