<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: ebhn</title><link>https://news.ycombinator.com/user?id=ebhn</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 23 Apr 2026 09:18:18 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=ebhn" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by ebhn in "Many SWE-bench-Passing PRs would not be merged"]]></title><description><![CDATA[
<p>Nice, I really like your idea. First I've heard of something like that</p>
]]></description><pubDate>Thu, 12 Mar 2026 00:53:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=47344819</link><dc:creator>ebhn</dc:creator><comments>https://news.ycombinator.com/item?id=47344819</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47344819</guid></item><item><title><![CDATA[New comment by ebhn in "Minions: Stripe’s one-shot, end-to-end coding agents"]]></title><description><![CDATA[
<p>Totally agree with this. When I review code I don't build a strong mental model of the system, and I think you can only really do that by solving the problems that arise during the creation of the system yourself. I'm optimistic the pendulum will swing away from the "hand off a spec to an agent(s)" and back towards engineers being engaged and directing LLMs to implement/optimize smaller, more specific pieces of code, with most of the direction being determined by the user</p>
]]></description><pubDate>Sun, 22 Feb 2026 16:12:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=47112166</link><dc:creator>ebhn</dc:creator><comments>https://news.ycombinator.com/item?id=47112166</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47112166</guid></item><item><title><![CDATA[New comment by ebhn in "Show HN: Portname – named localhost URLs for every dev server"]]></title><description><![CDATA[
<p>This is super useful. Thanks for sharing!</p>
]]></description><pubDate>Sat, 21 Feb 2026 17:44:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=47102927</link><dc:creator>ebhn</dc:creator><comments>https://news.ycombinator.com/item?id=47102927</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47102927</guid></item><item><title><![CDATA[New comment by ebhn in "Nobody knows how the whole system works"]]></title><description><![CDATA[
<p>I like this direction, but I worry about developers involvement in the design of the DSL becoming the new bottleneck with the same problems. The code which becomes the guardrails cannot just be generated slop, it should be thoroughly designed and understood imo</p>
]]></description><pubDate>Mon, 09 Feb 2026 22:26:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=46952411</link><dc:creator>ebhn</dc:creator><comments>https://news.ycombinator.com/item?id=46952411</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46952411</guid></item><item><title><![CDATA[New comment by ebhn in "Ask HN: What are you working on? (February 2026)"]]></title><description><![CDATA[
<p>Working on new code review tooling specifically for reviewing your own branches/commits when you use an "AI Agent" to assist with writing code. It seems all of the tools people are building in this space attempt to automate away the review, but I want better tools for reviewing (and tracking tech debt) in the code  I just generated locally. Will publish here soon</p>
]]></description><pubDate>Sun, 08 Feb 2026 19:39:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=46937733</link><dc:creator>ebhn</dc:creator><comments>https://news.ycombinator.com/item?id=46937733</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46937733</guid></item><item><title><![CDATA[New comment by ebhn in "I am happier writing code by hand"]]></title><description><![CDATA[
<p>Yea my job as a SWE is to have a correct mental model of the code and bing it with me everywhere I go... meetings, feature design, debugging sessions. Lines of code written is not unimportant, but matters way less when you look at the big picture</p>
]]></description><pubDate>Sun, 08 Feb 2026 16:19:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=46935660</link><dc:creator>ebhn</dc:creator><comments>https://news.ycombinator.com/item?id=46935660</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46935660</guid></item><item><title><![CDATA[New comment by ebhn in "Ask HN: Do you also "hoard" notes/links but struggle to turn them into actions?"]]></title><description><![CDATA[
<p>I think that for me with things like notes/writing, privacy is #1 by a lot. Preserving the textEdit workflow is nice, but I (and I imagine other users) could definitely be convinced to modify it given the right tooling and confidence in it. I know my workflow is not a productivity global maximum (and probably not even a local maximum), but everything I've seen so far does not justify itself as moving me far enough up on the productivity scale to offset the discomfort of changing habits.<p>Fwiw I really like the way you summarized the "constraint". Maybe I'm out of the loop on what's out there, but I don't think I've come across too many tools like that aside from lower level things like git.</p>
]]></description><pubDate>Sat, 07 Feb 2026 18:47:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=46926387</link><dc:creator>ebhn</dc:creator><comments>https://news.ycombinator.com/item?id=46926387</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46926387</guid></item><item><title><![CDATA[New comment by ebhn in "How to effectively write quality code with AI"]]></title><description><![CDATA[
<p>This is the main thing I have learned too. I've been building an internal tool for myself to annotate lines in each commit diff as good (green) / needs refactor (yellow) / needs rewrite (red) and it has helped me keep track of this kind of tech debt. Basically does what you could do with "TODO refactor" comments all over, but is more comprehensive and doesn't litter your source code. Plan to open source it once I've dog-fooded it a little more</p>
]]></description><pubDate>Sat, 07 Feb 2026 18:36:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=46926269</link><dc:creator>ebhn</dc:creator><comments>https://news.ycombinator.com/item?id=46926269</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46926269</guid></item><item><title><![CDATA[New comment by ebhn in "Software factories and the agentic moment"]]></title><description><![CDATA[
<p>That's hilarious</p>
]]></description><pubDate>Sat, 07 Feb 2026 18:26:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=46926185</link><dc:creator>ebhn</dc:creator><comments>https://news.ycombinator.com/item?id=46926185</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46926185</guid></item><item><title><![CDATA[New comment by ebhn in "Ask HN: Do you also "hoard" notes/links but struggle to turn them into actions?"]]></title><description><![CDATA[
<p>I actually like this idea, but most of my notes are scattered in untitled, unsaved textedit windows. It would be nice if I could run something locally that would access and scrape those unsaved notes, but would also leave them be. I don't think I'll ever stop having tons of these little note windows, but it would be nice if  I could request a summary or forgotten action items in my own time.</p>
]]></description><pubDate>Sat, 31 Jan 2026 00:03:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=46831708</link><dc:creator>ebhn</dc:creator><comments>https://news.ycombinator.com/item?id=46831708</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46831708</guid></item><item><title><![CDATA[New comment by ebhn in "I built a light that reacts to radio waves [video]"]]></title><description><![CDATA[
<p>Very cool!</p>
]]></description><pubDate>Fri, 23 Jan 2026 06:36:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=46729209</link><dc:creator>ebhn</dc:creator><comments>https://news.ycombinator.com/item?id=46729209</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46729209</guid></item><item><title><![CDATA[New comment by ebhn in "Ask HN: Share your personal website"]]></title><description><![CDATA[
<p><a href="https://www.ethanbond.dev/" rel="nofollow">https://www.ethanbond.dev/</a></p>
]]></description><pubDate>Wed, 14 Jan 2026 19:50:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=46621896</link><dc:creator>ebhn</dc:creator><comments>https://news.ycombinator.com/item?id=46621896</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46621896</guid></item><item><title><![CDATA[Show HN: Abstract Port Graphs]]></title><description><![CDATA[
<p>Abstract Port Graphs is a framework for building Domain Specific Languages (DSLs), where programs are represented as graphs. This project was created in pursuit of the ARC AGI challenge (more details on that at <a href="https://arcprize.org" rel="nofollow">https://arcprize.org</a>). By building a DSL on top of it for ARC puzzles, I was able to create compact solutions to the puzzles, which can be generated automatically via program synthesis techniques. The goal here was to explore program synthesis and symbolic AI approaches. The rationale for using graphs was the ability to detect isomorphisms between equivalent programs, leading to reusable components. The page includes additional links to the GitHub repo and a brief paper on the project. Would love feedback on the work, and to connect with anyone interested in ARC!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46526743">https://news.ycombinator.com/item?id=46526743</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 07 Jan 2026 14:29:40 +0000</pubDate><link>https://www.portgraphs.com/</link><dc:creator>ebhn</dc:creator><comments>https://news.ycombinator.com/item?id=46526743</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46526743</guid></item></channel></rss>