<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: japhyr</title><link>https://news.ycombinator.com/user?id=japhyr</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 18 Nov 2026 05:02:14 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=japhyr" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by japhyr in "New Evidence Shows School Phone Bans Are Gradually Improving Test Scores"]]></title><description><![CDATA[
<p>Absolutely. I was a high school teacher in the 2010s, and it was such a hard aspect of teaching to navigate.<p>For any reasonable phone policy to be implemented well, it has to come from the highest level of administration. It has to be enforced consistently across all levels from the district/principals down to individual classroom teachers. That requires a lot of people to understand the issue well, come to agreement, and be capable of enforcing difficult policies.<p>There are so many factors that make it difficult for this to happen. Parents who disagree with policies, often for valid reasons. Staff turnover makes consistency difficult. If one teacher lets students use phones, it makes it harder for everyone around them to manage the policy effectively. If groups of teachers don't adhere, it gets even harder.<p>This is no different than the impact of AirBnB on housing availability, especially in tourist destination towns. Tech companies create a situation that's really hard to manage, and then leave it to individuals and small organizations to manage something that really needs to be figured out at a societal level.</p>
]]></description><pubDate>Tue, 17 Nov 2026 14:22:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=50531788</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=50531788</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50531788</guid></item><item><title><![CDATA[New comment by japhyr in "Our software engineering interviews are changing a little"]]></title><description><![CDATA[
<p>I had lunch with a couple friends this week, and we each work in different tech environments. Most of the conversation was about the workflows we're each using, and seeing our colleagues use.<p>It's a really interesting time to work in this field. People who are paying attention to workflows are using a range of tools, and constantly refining their own workflow. For example a whole team might use Claude, but one person collects data about their own usage on an ongoing basis and develops more advanced workflows than everyone else on the team. Their focus isn't just about working faster, but about doing better work.<p>I don't think the post is vague; I think we're at a time where you need flexibility in your interview process to find candidates who are doing the best work these days.</p>
]]></description><pubDate>Thu, 12 Nov 2026 14:59:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=50468437</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=50468437</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50468437</guid></item><item><title><![CDATA[New comment by japhyr in "Ask HN: Are you using a custom harness?"]]></title><description><![CDATA[
<p>I've only implemented support for one provider at the moment, but it is structured in a way where I can add support for any other providers or local models. It feels good to not be locked into any one company's models or harness.</p>
]]></description><pubDate>Fri, 30 Oct 2026 12:23:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=50302949</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=50302949</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50302949</guid></item><item><title><![CDATA[Ask HN: Are you using a custom harness?]]></title><description><![CDATA[
<p>I was slow to adopt an agentic workflow for a variety of reasons. When I was ready to try an agentic workflow, I didn't want to install Claude on my own system. I have a hard time trusting its boundaries, and I don't want to spend a bunch of time learning its permissions model well enough to start trusting it.<p>I decided to write my own harness, and thought people would find that a pointless thing to do in 2026. I was amazed how easy it was to build a harness that can read, write, and modify files within a project directory. I now use this harness on a daily basis, and it hasn't grown much since that first iteration.<p>That made me wonder: How many of us are using a custom harness on a regular basis? What keeps you using your own harness?</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50301901">https://news.ycombinator.com/item?id=50301901</a></p>
<p>Points: 13</p>
<p># Comments: 11</p>
]]></description><pubDate>Fri, 30 Oct 2026 10:12:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=50301901</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=50301901</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50301901</guid></item><item><title><![CDATA[New comment by japhyr in "Harness Engineering 101: The LLM is the brain, the harness is the body"]]></title><description><![CDATA[
<p>I'm most familiar with Python, so I built a Textual app using an OpenAI API plan.<p>There's just two boxes to start with: an input message box for prompting, and a conversation box. Dump each input message into the conversation box. Post the response to the conversation box.<p>Once you get a prompt-and-response cycle going, you can start to define tools. A tool is a description of an action the model can request to carry out, and you write a function to implement that tool call. The tool descriptions get sent with each API call, and then the model can start calling tools as part of its response.<p>I added a box to clearly show the project directory, and a couple boxes to show which tools were being called and whether the model was attempting to cross any boundaries it shouldn't. A fun milestone is when you get to use the harness you're building to help build itself.<p>I didn't want to over abstract the implementation, but it's reasonably well structured. The TUI is separate from the tool definitions. The tool definitions are model-agnostic. Everything specific to OpenAI is in an openai_model.py file. If I want to use Anthropic models, I could add an anthropic_model.py file. Or I could make it all local and add a local_model.py file.<p>I'm not working with subagents yet, but I can see a way to implement that if I end up wanting to.<p>The OpenAI Python library makes these interactions really straightforward to implement:<p><a href="https://github.com/openai/openai-python" rel="nofollow">https://github.com/openai/openai-python</a></p>
]]></description><pubDate>Mon, 19 Oct 2026 14:59:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=50153317</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=50153317</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50153317</guid></item><item><title><![CDATA[New comment by japhyr in "Harness Engineering 101: The LLM is the brain, the harness is the body"]]></title><description><![CDATA[
<p>Yes, it's so easy to build a harness for a lot of use cases now, and you learn so much from doing so.<p>I'm a solo developer, and I didn't want to sort out all the boundaries and permissions of Claude or other heavy harnesses. All I wanted was something that can read, write, and modify files in a project directory. I gave myself three days to see if I could make a harness that was complete enough to work on my own projects. It was usable in less than a day.<p>I love using it, because I know exactly what its boundaries are, and how they're enforced. When I need more features I can either implement them in my own harness, or choose a heavier harness with much clearer understanding of what to look for.</p>
]]></description><pubDate>Mon, 19 Oct 2026 14:05:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=50152694</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=50152694</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50152694</guid></item><item><title><![CDATA[New comment by japhyr in "AI coding agents generate more code, but not more software"]]></title><description><![CDATA[
<p>When people have gotten excited about having so many tests, I've asked them what their plan is when 500 of their 1000 test suddenly stop passing. I've always favored 50 tests I know are meaningful, where any failure is something to respond to, over 500 tests with a bunch of overlap and edge cases I'm not sure matter. But now people aren't even thinking about that, they're just letting the agents make all those decisions.<p>I think this approach will continue to work for some people and orgs, but others are going to hit walls where their agents can't manage the mountains anymore. It's going to be interesting to see how people and orgs respond when that happens.</p>
]]></description><pubDate>Mon, 12 Oct 2026 18:05:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=50060331</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=50060331</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50060331</guid></item><item><title><![CDATA[New comment by japhyr in "US imposes sanctions on ICC hours after former judge wins Nobel Peace Prize"]]></title><description><![CDATA[
<p>He doesn't really think, he reacts. And his every reaction is centered around "How can I make this about me?"</p>
]]></description><pubDate>Fri, 09 Oct 2026 16:10:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=50022620</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=50022620</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50022620</guid></item><item><title><![CDATA[New comment by japhyr in "AI and the Destruction of the Creative Commons"]]></title><description><![CDATA[
<p>I like this article. We've read a lot of takes quite similar to this, and I think it's worth continuing to write and share reflections just like this.<p>> Yet, through much effort and 40 years of debate we had reached an equilibrium. Now AI has thrown that out the window.<p>The only thing I'd like to add here is that "AI" in this sentence should really be read as "the companies building frontier AI models have thrown this out the window". I don't necessarily think the author should have used a phrase like that, because it gets quite pedantic to read posts where such precise language is used all the time. But when we talk about where to go as an industry and as a society, we need to keep that distinction in mind.<p>The tech is here to stay, but the tech itself is not what's thrown our norms out the window. It's the people running these companies who are putting their vision and their profits above everyone else in the world. Most of us are exploring this tech and trying to figure out what it's useful for. It's a much harder question to try and figure out what to do about the people using this tech to consolidate wealth and power. We can't hold a technology responsible for anything, but we can hold people responsible for their impact on everyone else.</p>
]]></description><pubDate>Sun, 20 Sep 2026 11:49:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=49774864</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=49774864</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49774864</guid></item><item><title><![CDATA[New comment by japhyr in "Learning Programming in an Age of LLMs"]]></title><description><![CDATA[
<p>I'm the author of Python Crash Course, and I got this exact same email this week. I was thinking of writing a public response as well, because any attempt to sincerely answer these questions takes something along the lines of a full post. It's also worth a public response because many people who are getting into programming for the first time right now are asking variations of these same questions.<p>> Do I think that AI enables people to develop faster than they can keep up?<p>Absolutely. That's the core of this person's email, and everyone else who asks similar questions. Just five years ago, the only way to build a working project of moderate complexity was to learn the basic to intermediate concepts required to make an MVP. Now, if you can steer an LLM reasonably well, you can quickly build an MVP that goes well beyond your own understanding of the implementation.<p>I don't think anyone has clear answers to all the questions brought up in this email. I think people can learn faster than they used to, because they can make connections between different areas faster than they used to. But it requires skill and discipline in how you learn, and how you work. You have to intentionally build your understanding as you build your projects.</p>
]]></description><pubDate>Wed, 16 Sep 2026 10:05:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=49724240</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=49724240</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49724240</guid></item><item><title><![CDATA[New comment by japhyr in "Initial effects of AI technology on employment look positive"]]></title><description><![CDATA[
<p>Are you seeing companies that are in over their heads because they don't have enough domain knowledge?<p>I think that's always been an issue in tech, but it feels like AI exacerbates the issue. I see people starting companies and services where their primary domain knowledge seems to be whatever their AI tells them. It's sometimes enough to get off the ground, but I wonder how long it takes for customers/clients who actually need the domain knowledge to bail.</p>
]]></description><pubDate>Mon, 07 Sep 2026 14:58:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=49599166</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=49599166</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49599166</guid></item><item><title><![CDATA[New comment by japhyr in "Barrier lake continues to pose flood risk, China warns"]]></title><description><![CDATA[
<p>For a bit of context, Juneau Alaska deals with a smaller scale version of this most years. There's a bowl off of the Mendenhall Glacier named Suicide Basin. Each summer that basin gets filled with meltwater, which forms a lake because the glacier blocks the water from leaving the basin. At some point the lake fills with enough water that part of the blockage gives way and the lake suddenly releases.<p>In Juneau, this is a well-defined basin with well-established dynamics. The city still wrestles with how best to handle this. Recent years have seen higher river levels when the basin releases, and the downstream banks of the Mendenhall River have eroded much faster than people were expecting. The city and individual homeowners are engaged in multiple projects to manage the annual flooding.<p>In the Nepal case the scale is much larger, and the variables are less known and less stable. This is absolutely devastating to see.<p><a href="https://www.adn.com/alaska-news/2026/08/12/juneau-officials-urge-residents-in-glacial-flood-prone-areas-to-evacuate-ahead-of-rivers-crest/" rel="nofollow">https://www.adn.com/alaska-news/2026/08/12/juneau-officials-...</a></p>
]]></description><pubDate>Fri, 28 Aug 2026 17:35:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=49481908</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=49481908</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49481908</guid></item><item><title><![CDATA[New comment by japhyr in "How I over-engineered my book"]]></title><description><![CDATA[
<p>> I did a full (human) blank page rewrite three days ago<p>You did a "blank page rewrite" of a 576 page book "three days ago"?</p>
]]></description><pubDate>Tue, 18 Aug 2026 17:05:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=49348812</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=49348812</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49348812</guid></item><item><title><![CDATA[New comment by japhyr in "My friends all hate AI; I just joined an AI startup"]]></title><description><![CDATA[
<p>Of course everyone hates AI. For most people, it's actively making their lives worse, not better.<p>AI is a really effective technology when used with restraint, in appropriate places. But it's rarely being used with restraint, and it's being inserted just about everywhere.<p>If you're trying to work in AI on a product related to education, you've got a really high bar to clear to prove that you're actually helping students learn better, and teachers teach better.</p>
]]></description><pubDate>Mon, 17 Aug 2026 23:14:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=49338990</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=49338990</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49338990</guid></item><item><title><![CDATA[New comment by japhyr in "Show HN: I replaced a $120k bowling center system with $1,600 in ESP32s"]]></title><description><![CDATA[
<p>Where are you located? Around 2020 I put together a landslide risk monitoring site that's entirely based on stream gauges:<p><a href="https://khmpsitka.org" rel="nofollow">https://khmpsitka.org</a><p>It's an interesting approach that's way simpler than relying on soil moisture sensors placed high up on mountainsides. It's not as widely applicable as measuring soil moisture directly, but it's been running steadily for over 5 years now.</p>
]]></description><pubDate>Mon, 20 Jul 2026 10:53:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=48977012</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=48977012</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48977012</guid></item><item><title><![CDATA[New comment by japhyr in "Show HN: 18 Words"]]></title><description><![CDATA[
<p>I didn't see this until this morning, and the continuing through for the whole 18 words was a really good experience. I got 14/18, and that was much more satisfying than ending at my first failure.</p>
]]></description><pubDate>Fri, 10 Jul 2026 12:17:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=48858865</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=48858865</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48858865</guid></item><item><title><![CDATA[New comment by japhyr in "Bonnie Tyler has died"]]></title><description><![CDATA[
<p>Growing up in the 80s, I've known (and sung) this song all my life. But I just saw this flowchart for the first time today:<p><a href="https://jeannr.tumblr.com/post/165291081/i-made-a-flow-chart-that-we-might-better" rel="nofollow">https://jeannr.tumblr.com/post/165291081/i-made-a-flow-chart...</a><p>I believe that's the original source, but it looks cut off. Here's a full version:<p><a href="https://i.pinimg.com/originals/b1/82/dc/b182dcc291495c013c9820abef8c087a.jpg" rel="nofollow">https://i.pinimg.com/originals/b1/82/dc/b182dcc291495c013c98...</a></p>
]]></description><pubDate>Thu, 09 Jul 2026 13:02:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=48845165</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=48845165</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48845165</guid></item><item><title><![CDATA[New comment by japhyr in "The deadly rise of giant trucks and SUVs"]]></title><description><![CDATA[
<p>When vehicles were starting to get noticeably bigger about 20 years ago, I asked some family members why they were buying vehicles they had to climb up into.<p>"On the highway, I'd rather kill someone than be killed in a wreck."<p>They would not recognize that while that might work for a while, it wasn't going to lead anywhere good for our society. A generation of people thinking like that has filled our roads with vehicles that protect their occupants while making it more dangerous for everyone else.</p>
]]></description><pubDate>Tue, 23 Jun 2026 19:11:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=48649866</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=48649866</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48649866</guid></item><item><title><![CDATA[New comment by japhyr in "Python 3.14 garbage collection rigamarole"]]></title><description><![CDATA[
<p>> In fact, I think Guido himself resigned due to the experience he had trying to get a PEP through the committee.<p>If you're referring to the steering council, that group was created in response to Guido stepping down.<p>He stepped down partly in response to the changing nature of online discussions around changes to the language. He just didn't want to be at the center of every polarizing discussion anymore. I think he also recognized that the transition needed to happen at some point, and that was as good a time as any.</p>
]]></description><pubDate>Sun, 14 Jun 2026 10:35:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=48525936</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=48525936</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48525936</guid></item><item><title><![CDATA[New comment by japhyr in "Lines of Code Got a Better Publicist"]]></title><description><![CDATA[
<p>> But adoption is the starting line, not the scoreboard.<p>Yes yes, shout it from the rooftops! Over the next few years I think we're going to see that companies that get this point will keep doing meaningful things, and stand a chance of weathering this transition period.<p>I think we're going to see a bunch of companies that went all in on AI for AI's sake go under because they've lost their mission, lost their implementation, and won't have a way to get those back in a reasonable timeframe and at a reasonable cost.</p>
]]></description><pubDate>Thu, 11 Jun 2026 16:05:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=48492238</link><dc:creator>japhyr</dc:creator><comments>https://news.ycombinator.com/item?id=48492238</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48492238</guid></item></channel></rss>