<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: vetronauta</title><link>https://news.ycombinator.com/user?id=vetronauta</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 09 Sep 2026 15:54:26 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=vetronauta" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by vetronauta in "How well do agents use test/verification techniques?"]]></title><description><![CDATA[
<p>If I understood correctly, the author had the agent perform <i>manual</i> mutation testing (write code, write passing tests, manually change the code to see some tests fail, then revert the change), rather than <i>automated</i> mutation testing. Why not use a mutation-testing framework and consider the build failed if a certain percentage of mutations are not killed?<p>The article claims that the agents didn’t actually use TDD or mutation testing. While it’s possible for an agent to ignore the TDD procedure even when instructed to follow it, it can’t ignore a build failure.</p>
]]></description><pubDate>Tue, 08 Sep 2026 04:51:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=49605704</link><dc:creator>vetronauta</dc:creator><comments>https://news.ycombinator.com/item?id=49605704</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49605704</guid></item><item><title><![CDATA[New comment by vetronauta in "Formalizing Fermat's Last Theorem"]]></title><description><![CDATA[
<p>Currently a tiny fraction of what is formalizable is of interest to mathematics; maybe humans will stop doing "serious" mathematics, but mathematics is beautiful and we will not stop playing with math, like we did not stop playing chess.<p>I would love to see a theory in the spirit of Guerino Mazzola work, but for (combinatorial) games.</p>
]]></description><pubDate>Sat, 05 Sep 2026 18:56:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=49579547</link><dc:creator>vetronauta</dc:creator><comments>https://news.ycombinator.com/item?id=49579547</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49579547</guid></item><item><title><![CDATA[New comment by vetronauta in "Does code cleanliness affect coding agents? A controlled minimal-pair study"]]></title><description><![CDATA[
<p>I was reading your comment, disagreeing with it but still feeling why this is a good comment. It just occurred to me that this is not science: science must be reproducible and this is just an historical report on artifact that will be unavailable soon.</p>
]]></description><pubDate>Mon, 06 Jul 2026 05:39:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=48801026</link><dc:creator>vetronauta</dc:creator><comments>https://news.ycombinator.com/item?id=48801026</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48801026</guid></item><item><title><![CDATA[Leanstral 1.5]]></title><description><![CDATA[
<p>Article URL: <a href="https://docs.mistral.ai/models/model-cards/leanstral-1-5-26-06">https://docs.mistral.ai/models/model-cards/leanstral-1-5-26-06</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48738938">https://news.ycombinator.com/item?id=48738938</a></p>
<p>Points: 310</p>
<p># Comments: 149</p>
]]></description><pubDate>Tue, 30 Jun 2026 20:44:56 +0000</pubDate><link>https://docs.mistral.ai/models/model-cards/leanstral-1-5-26-06</link><dc:creator>vetronauta</dc:creator><comments>https://news.ycombinator.com/item?id=48738938</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48738938</guid></item><item><title><![CDATA[New comment by vetronauta in "Historic co-determination helps monasteries navigate digital change"]]></title><description><![CDATA[
<p><a href="https://en.wikipedia.org/wiki/Buddhas_of_Bamiyan" rel="nofollow">https://en.wikipedia.org/wiki/Buddhas_of_Bamiyan</a>
<a href="https://en.wikipedia.org/wiki/List_of_destroyed_libraries" rel="nofollow">https://en.wikipedia.org/wiki/List_of_destroyed_libraries</a></p>
]]></description><pubDate>Sun, 14 Jun 2026 12:18:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=48526498</link><dc:creator>vetronauta</dc:creator><comments>https://news.ycombinator.com/item?id=48526498</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48526498</guid></item><item><title><![CDATA[New comment by vetronauta in "Software Architecture Guide (2019)"]]></title><description><![CDATA[
<p>If writing code is tactics, architecture is strategy. The end goal is just the desired outcome.</p>
]]></description><pubDate>Sun, 14 Jun 2026 06:49:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=48524800</link><dc:creator>vetronauta</dc:creator><comments>https://news.ycombinator.com/item?id=48524800</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48524800</guid></item><item><title><![CDATA[Magit manuals are available online again]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/magit/magit/issues/5472">https://github.com/magit/magit/issues/5472</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45926037">https://news.ycombinator.com/item?id=45926037</a></p>
<p>Points: 128</p>
<p># Comments: 58</p>
]]></description><pubDate>Fri, 14 Nov 2025 12:09:59 +0000</pubDate><link>https://github.com/magit/magit/issues/5472</link><dc:creator>vetronauta</dc:creator><comments>https://news.ycombinator.com/item?id=45926037</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45926037</guid></item></channel></rss>