<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: aocallaghan17</title><link>https://news.ycombinator.com/user?id=aocallaghan17</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 21 Jun 2026 15:23:02 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=aocallaghan17" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by aocallaghan17 in "Coding agents have no moat"]]></title><description><![CDATA[
<p>The models are the moat. It's why you have generous subscription usage plans and increasingly limited third party access.</p>
]]></description><pubDate>Mon, 15 Jun 2026 18:21:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=48545127</link><dc:creator>aocallaghan17</dc:creator><comments>https://news.ycombinator.com/item?id=48545127</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48545127</guid></item><item><title><![CDATA[Show HN: I used Claude to build my son a Minecraft phonics game]]></title><description><![CDATA[
<p>Article URL: <a href="https://alexocallaghan.com/minecraft-phonics-game">https://alexocallaghan.com/minecraft-phonics-game</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48537272">https://news.ycombinator.com/item?id=48537272</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 15 Jun 2026 06:17:08 +0000</pubDate><link>https://alexocallaghan.com/minecraft-phonics-game</link><dc:creator>aocallaghan17</dc:creator><comments>https://news.ycombinator.com/item?id=48537272</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48537272</guid></item><item><title><![CDATA[New comment by aocallaghan17 in "Not everyone is using AI for everything"]]></title><description><![CDATA[
<p>Reminds me of this article: <a href="https://www.theverge.com/podcast/917029/software-brain-ai-backlash-databases-automation" rel="nofollow">https://www.theverge.com/podcast/917029/software-brain-ai-ba...</a><p>Software engineers are definitely in a bit of a bubble here. Are we just early adopters who see the value sooner, or does it uniquely benefit software engineering, or do we just like cool automation and we're deluding ourselves that this adds value beyond the cost?</p>
]]></description><pubDate>Sun, 14 Jun 2026 15:32:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=48528308</link><dc:creator>aocallaghan17</dc:creator><comments>https://news.ycombinator.com/item?id=48528308</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48528308</guid></item><item><title><![CDATA[New comment by aocallaghan17 in "Loop Engineering: Designing loops that prompt coding agents"]]></title><description><![CDATA[
<p>Yeah I mean this is closer to my use of LLMs, where I'm intentionally slowing things down enough to follow and course correct myself. This whole build the loop not the prompt idea seems to be advocating the opposite... I don't feel comfortable to not be the driver of the loop for a production system.</p>
]]></description><pubDate>Sat, 13 Jun 2026 19:58:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=48520841</link><dc:creator>aocallaghan17</dc:creator><comments>https://news.ycombinator.com/item?id=48520841</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48520841</guid></item><item><title><![CDATA[New comment by aocallaghan17 in "Loop Engineering: Designing loops that prompt coding agents"]]></title><description><![CDATA[
<p>I'm just struggling with this, surely you need inner depth knowledge to reason about the system and make some level of decision, at least around system design and architecture if not lower level implementation details? But it sounds like you're generating that knowledge each time through a system of agents? How do you have so much trust in a non-deterministic system, or are you deferring ALL decisions to these "loops"? What if you and a team member generate a dashboard and it gives different results because the agent(s) used a different methodology?<p>And surely cost plays a part here. This is giving you such productivity gains to boost revenue enough to outweigh what must be huge token costs?</p>
]]></description><pubDate>Sat, 13 Jun 2026 19:55:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=48520816</link><dc:creator>aocallaghan17</dc:creator><comments>https://news.ycombinator.com/item?id=48520816</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48520816</guid></item><item><title><![CDATA[New comment by aocallaghan17 in "Vercel Drop"]]></title><description><![CDATA[
<p>Seems like it. Perhaps the use case is for non-engineering folks to share AI generated prototypes?<p>We're starting to get asked by product managers how they can share/deploy their prototypes they made with Claude/Cursor.</p>
]]></description><pubDate>Sat, 13 Jun 2026 17:29:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=48519413</link><dc:creator>aocallaghan17</dc:creator><comments>https://news.ycombinator.com/item?id=48519413</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48519413</guid></item><item><title><![CDATA[New comment by aocallaghan17 in "Automating myself out of development"]]></title><description><![CDATA[
<p>Agree with this completely. This push for more autonomy I think is the complete wrong direction for how to use LLMs.<p>I want less code to maintain not more that I don't even fully understand.<p>I think research and very supervised coding with lots of guardrails is the way to actually gain productivity from these tools.</p>
]]></description><pubDate>Sat, 13 Jun 2026 13:48:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=48517323</link><dc:creator>aocallaghan17</dc:creator><comments>https://news.ycombinator.com/item?id=48517323</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48517323</guid></item><item><title><![CDATA[New comment by aocallaghan17 in "Loop Engineering: Designing loops that prompt coding agents"]]></title><description><![CDATA[
<p>I just don't see any way you can work like this and maintain comprehension of the system being built?<p>Perhaps for toy projects or research, but for a production system you're accountable for understanding, maintaining and continuing to develop?</p>
]]></description><pubDate>Sat, 13 Jun 2026 10:26:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=48515688</link><dc:creator>aocallaghan17</dc:creator><comments>https://news.ycombinator.com/item?id=48515688</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48515688</guid></item><item><title><![CDATA[New comment by aocallaghan17 in "The PM Trap: AI Won't Turn Engineers into Managers"]]></title><description><![CDATA[
<p>Agreed, and if automating the creation just creates more of these issues, faster than we can solve them, is it actually making us more productive?</p>
]]></description><pubDate>Sat, 13 Jun 2026 10:21:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=48515639</link><dc:creator>aocallaghan17</dc:creator><comments>https://news.ycombinator.com/item?id=48515639</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48515639</guid></item><item><title><![CDATA[New comment by aocallaghan17 in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"]]></title><description><![CDATA[
<p>The huge investment into LLMs at a loss is about having control of these tools and technology. Now we're seeing a state try to take some control.<p>But who do you trust more to make these decisions? A democratically elected government or a private company?</p>
]]></description><pubDate>Sat, 13 Jun 2026 08:32:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=48514922</link><dc:creator>aocallaghan17</dc:creator><comments>https://news.ycombinator.com/item?id=48514922</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48514922</guid></item></channel></rss>