<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: abalgir</title><link>https://news.ycombinator.com/user?id=abalgir</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 19 Oct 2026 12:20:12 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=abalgir" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by abalgir in "AI Can Write the Code. Who Verifies It?"]]></title><description><![CDATA[
<p>I agree with you on this one; the compiler output remains the same if run the next day, but AI code might not. That is why you need a strong, independent reviewer who reviews the AI code and freezes it after verification, so that next time you do not have to ask the AI to regenerate the code.</p>
]]></description><pubDate>Sat, 17 Oct 2026 21:14:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=50135193</link><dc:creator>abalgir</dc:creator><comments>https://news.ycombinator.com/item?id=50135193</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50135193</guid></item><item><title><![CDATA[New comment by abalgir in "How the Claude Code team does code review"]]></title><description><![CDATA[
<p>Fair assumption. I think humans, at least those who like to code and build solutions, will become better builders than coders. Understanding the code will become less important, but knowing how to put it all together will be essential.</p>
]]></description><pubDate>Sat, 17 Oct 2026 20:58:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=50135066</link><dc:creator>abalgir</dc:creator><comments>https://news.ycombinator.com/item?id=50135066</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50135066</guid></item><item><title><![CDATA[New comment by abalgir in "How the Claude Code team does code review"]]></title><description><![CDATA[
<p>I agree with you. A code reviewer from the same company, even with different models or efforts, shares the same blind spots. To review my code, I use a different company; if I code with Claude (usually Sonnet 5.5-medium), Codex reviews it, and vice versa. I get much better code this way. But more importantly, I always tell the reviewer to build its own test-scenario ledger and refute the coder's claim that it is done. And the verdict is shared with the coder, but the coder cannot reject it.</p>
]]></description><pubDate>Sat, 17 Oct 2026 20:51:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=50135030</link><dc:creator>abalgir</dc:creator><comments>https://news.ycombinator.com/item?id=50135030</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50135030</guid></item><item><title><![CDATA[New comment by abalgir in "Show HN: Connectio – One local address for all your development servers"]]></title><description><![CDATA[
<p>very interesting, i will give it a try. Thank you</p>
]]></description><pubDate>Sat, 17 Oct 2026 20:11:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=50134665</link><dc:creator>abalgir</dc:creator><comments>https://news.ycombinator.com/item?id=50134665</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50134665</guid></item><item><title><![CDATA[New comment by abalgir in "Show HN: CoastMath: (Open Source) Personal Finance and Retirement Planner"]]></title><description><![CDATA[
<p>Very interesting using subscription instead of API.</p>
]]></description><pubDate>Sat, 17 Oct 2026 20:09:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=50134648</link><dc:creator>abalgir</dc:creator><comments>https://news.ycombinator.com/item?id=50134648</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50134648</guid></item></channel></rss>