<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: vydra</title><link>https://news.ycombinator.com/user?id=vydra</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 16 Apr 2026 05:04:34 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=vydra" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by vydra in "We're in the wrong moment"]]></title><description><![CDATA[
<p>Its definitely much harder to get into the industry than it was a few years ago and if its coding you were after, you may indeed be disappointed. But give Software Engineering a try! We need to rewrite many of our critical systems and we are afraid to do so primarily to the lack of truly skilled software engineers. IMHO, the AI agents are creating time for us to study what really matters. I would start with Modern Software Engineering by Dave Farley. DM me directly if you want to chat on this topic. <a href="https://www.linkedin.com/in/dvydra/" rel="nofollow">https://www.linkedin.com/in/dvydra/</a></p>
]]></description><pubDate>Mon, 27 Oct 2025 06:03:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=45717851</link><dc:creator>vydra</dc:creator><comments>https://news.ycombinator.com/item?id=45717851</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45717851</guid></item><item><title><![CDATA[New comment by vydra in "Test-driven development with an LLM for fun and profit"]]></title><description><![CDATA[
<p>We implemented something similar for our Java backend project based on my rant here: <a href="https://testdriven.com/testdriven-2-0-8354e8ad73d7" rel="nofollow">https://testdriven.com/testdriven-2-0-8354e8ad73d7</a> Works great! I only look at generated code if it passes the tests. Now, can we use LLMs to generate tests from requirements? Maybe, but tests are mostly declarative and are easier to write than production code most of the time. This approach also allows us to use cheaper models, because the tool will automatically tell the model about compile error and failed tests. Usually, we give it up to five attempts to fix the code.</p>
]]></description><pubDate>Fri, 17 Jan 2025 01:43:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=42733161</link><dc:creator>vydra</dc:creator><comments>https://news.ycombinator.com/item?id=42733161</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42733161</guid></item><item><title><![CDATA[New comment by vydra in "Why Copilot Is Making Programmers Worse at Programming"]]></title><description><![CDATA[
<p>I found the error rate of Copilot unacceptable for most of my daily work, so 2 months ago we kicked off a project to write a tool more appropriate for someone who practices TDD -- specifically, I don;t want to see generated code unless it passes my tests. The early results are very promising for my stack which is backend Java/Spring. See <a href="https://testdriven.com/testdriven-2-0-8354e8ad73d7" rel="nofollow">https://testdriven.com/testdriven-2-0-8354e8ad73d7</a></p>
]]></description><pubDate>Wed, 11 Sep 2024 19:51:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=41514776</link><dc:creator>vydra</dc:creator><comments>https://news.ycombinator.com/item?id=41514776</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41514776</guid></item></channel></rss>