<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: coreyp_1</title><link>https://news.ycombinator.com/user?id=coreyp_1</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 30 Jun 2026 05:32:29 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=coreyp_1" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by coreyp_1 in "HamsterOS: A graphical desktop OS that fits on a 1.44MB floppy"]]></title><description><![CDATA[
<p>That's great!  I see it as a lot of people learning about a lot of cool stuff that interests them.<p>Just because AI was used doesn't mean that it wasn't valuable to that person as an experience, and that it's not also valuable to someone else.<p>I say good job on shipping a project!</p>
]]></description><pubDate>Mon, 29 Jun 2026 16:59:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=48721826</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=48721826</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48721826</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Ask HN: Why don't LLM harnesses enable/expose custom middleware hooks?"]]></title><description><![CDATA[
<p>Yes, that sounds like something that a harness would do internally, but not expose.  My own project will do something similar for spinning off worker agents.  You could expose it, however, by (1) a custom MCP server that assembles and provides the result directly into the context, or (2) see if you can wrangle the skill feature of an existing harness.<p>The newer models are nice, but the harness is the secret sauce that can make or break the experience.  I wish we had better open tools for using/modifying these types of things.</p>
]]></description><pubDate>Thu, 25 Jun 2026 07:11:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=48670002</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=48670002</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48670002</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Ask HN: Do you have an unusual income source"]]></title><description><![CDATA[
<p>In the future, some LLM will incorporate this into their side-hustle suggestions. :)</p>
]]></description><pubDate>Wed, 24 Jun 2026 20:52:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=48665472</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=48665472</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48665472</guid></item><item><title><![CDATA[New comment by coreyp_1 in "What's the worst thing your AI agent did in production without asking first?"]]></title><description><![CDATA[
<p>In our company, Claude keeps trying to run terraform commands (another team member's experience).  Thankfully, it's in a locked-down environment, but it still keeps trying, even if you tell it not to.<p>In development, it will sometimes do all sorts of wild and convoluted things because the conversation has been compressed and it suddenly can't remember the structure of the project or other critical instructions.<p>AI should <i>never</i> have access to a production environment.  Ever.  Thankfully, we enforce that.</p>
]]></description><pubDate>Wed, 24 Jun 2026 20:48:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=48665433</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=48665433</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48665433</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Ask HN: Why don't LLM harnesses enable/expose custom middleware hooks?"]]></title><description><![CDATA[
<p>I <i>am</i> writing my own harness, and I would love to hear more about what you have in mind.<p>Can you give an example of your use case?</p>
]]></description><pubDate>Wed, 24 Jun 2026 20:33:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=48665276</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=48665276</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48665276</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Anthropic apologizes for invisible Claude Fable guardrails"]]></title><description><![CDATA[
<p>With 128 GB strix halo, you can't do as big of a model as you would think. You can do larger than having a single graphics card, of course, but that 128 gigs cannot all be dedicated to the model. Remember, the context alone is usually larger than the model itself.  I got an EVO X2, and I don't regret it, but by my current calculations, it will take 8 years to recoup the cost, as opposed to just using equivalent, paid commercial options.</p>
]]></description><pubDate>Fri, 12 Jun 2026 02:09:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=48499015</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=48499015</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48499015</guid></item><item><title><![CDATA[New comment by coreyp_1 in "SoulsOnly.tff – A font for humans not AI and keyboard firmware to type in it"]]></title><description><![CDATA[
<p>They meant that this is a technique that relies on a person's <i>vision</i>, which means that the blind, by definition, are being excluded.  They weren't being hostile toward the blind, they were pointing out that the project <i>itself</i> is hostile towards the blind.</p>
]]></description><pubDate>Mon, 08 Jun 2026 17:27:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=48448292</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=48448292</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48448292</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Hybrid local and cloud LLM stack for regulated financial document processing?"]]></title><description><![CDATA[
<p>There are so many variables here. My question is how much do you have to invest into getting it done right?<p>Local has come a long way, but it is still limited and slow. And while there are some people who have done stuff like this, the field is so new that you're probably going to get someone that doesn't have direct experience with everything. In other words, they're going to get stuff wrong. You will have to rebuild some part of it. You might not purchase the right hardware. Can you live with this?<p>In all fairness, though, if you have someone who has experience in evaluating new systems and using them to build something, then you can still be in good shape. I mentioned this, simply because it's a skill that is not as common as we would like in this world. Just look for someone with a track record of delivering functional software using new technologies.<p>My personal bias is that I love to keep as much local as possible, but I also realize that I bought a $3,000 machine that so far has saved me $5 in tokens from an external API. As I see it, the only real reasons to have local AI at the moment is privacy, but that does fit your use case.<p>As for a turnkey solution, they have their benefits, but their moat is significantly smaller now than it used to be. Quite frankly, you can vibe code the majority of TurnKey solutions in a weekend. Well, at least the parts that you need.<p>Sorry to not give more specific answers, but a lot of your questions may depend on whichever developer you decide to use. There's not necessarily a wrong answer in many cases, there are multiple paths to achieve what you are trying to do. If I were you, I would focus on long-term maintainability and security of your system. For example, you can have the best thing in the world, but if you can't pass a SOC2 (or, even worse, your developer has never heard of something like that) then you are going to be in a lot of pain.</p>
]]></description><pubDate>Fri, 29 May 2026 18:38:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=48327462</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=48327462</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48327462</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Ask HN: Any advice on how to learn good software architecture practices?"]]></title><description><![CDATA[
<p><a href="https://aosabook.org/en/" rel="nofollow">https://aosabook.org/en/</a><p>These are available to read completely free online, but I do plan to purchase the physical books some day.<p>[edit] I realize that I should probably give more context to my answer.  The books on the site are basically interviews with the authors of the software and they discuss what choices they made as well as the advantages/tradeoffs of this approach.  In other words, the direct answer to your question is to learn by reading what other people have written about their own successes and glean from that.<p>[edit 2] Your favorite LLM could also provide a list of books that are similar in spirit, but there's just something about the series that I linked to that I like.</p>
]]></description><pubDate>Fri, 29 May 2026 16:42:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=48325671</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=48325671</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48325671</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Ask HN: Anyone else struggling with AI and work?"]]></title><description><![CDATA[
<p>This resonates with me, but what helped was to come to a realization.<p>I love coding. I love low level coding. But I haven't written any code in the last 6 months, roughly.<p>But I don't feel empty or dissatisfied at all. My realization for myself is that I love solving problems and designing elegant solutions. Using AI, I still have to do that. I still have to make choices about how I want specified modules to interoperate. I know the big picture, and can catch when the AI is taking a shortcut.<p>I realized that it is all still low level design in my eyes. And I enjoy doing it, whether with my own hands, or with AI.<p>The amazing thing with AI, though, is that it has allowed me to explore so many things much quicker than I could before. It's still my design, my ideas, and even my poor choices that I have to deal with, but it reduces the boiler plate, so to speak.<p>That, and it has allowed me to explore more than I ever dreamed that I would be able experience.</p>
]]></description><pubDate>Fri, 22 May 2026 18:39:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=48239701</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=48239701</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48239701</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Built AI forensic accounting software with my dad"]]></title><description><![CDATA[
<p>Nice.  I have a friend who is a young accountant.  I have tried to get him to consider AI, but he claims that they tried it and it's not that good.  I've tried to get him to understand that AI has improved dramatically in the last few months, not to mention the last few years (their point of reference, I believe).</p>
]]></description><pubDate>Fri, 22 May 2026 16:38:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=48238243</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=48238243</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48238243</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Blog ran on Ubuntu 16.04 for 10 years. I migrated it to FreeBSD"]]></title><description><![CDATA[
<p>I'm in the same boat.  I have 2 old servers that I let get "too" old, and now I'm afraid to touch them to update them.  However, with some of the shenanigans that the Linux distributions are pulling around age verification/attestation, I'm considering bailing on them entirely.<p>Note, I did try Artix, but when it broke last week after a restart (in which evidently something had gone wrong with an earlier kernel update), and I had to pull out a rescue ISO, I decided I didn't want to mess with that.  I switched that machine to Devuan, but the jury is still out for me.  I don't have any major complaints, but I'm still in the burn-in phase. :)  I'm running Arch on a laptop, but they have been a bit hostile in the community with censorship, so I'm just waiting for a free weekend to blast it and put something else on.  I don't want political drama in my software.<p>This all comes at an interesting time, though.  This is the first time that I purchased a new laptop and didn't even let it boot into Windows, but instantly installed Linux.  And everything "just worked".  And now that I'm excited to try Linux, so many of the big players are embracing the steps to erode privacy (AI everywhere... age attestation/verification... telemetry on by default...).  It's sad, and I'm just going to "nope" out of any interactions with them.</p>
]]></description><pubDate>Thu, 21 May 2026 21:11:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=48228949</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=48228949</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48228949</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Ask HN: Any recommendataions for exporting data from Amazon?"]]></title><description><![CDATA[
<p>In anyone in the future is reading this, I ended up vibe-coding a chrome plugin to let me pull the page info as a MCP call.  It's working (and I successfully can extract data) using Qwen 3.6 locally (GMKTec EVO-X2, 128GiB RAM).</p>
]]></description><pubDate>Thu, 07 May 2026 21:03:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=48054969</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=48054969</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48054969</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Ask HN: Any recommendataions for exporting data from Amazon?"]]></title><description><![CDATA[
<p>Thank you for your reply, but I haven't paid for Claude, and I don't plan to with my other subscriptions. Plus, I'm trying to have this be part of my headless automation with my own, local llms. If it weren't hacked together, it wouldn't be appropriate for this website in the first place! LOL</p>
]]></description><pubDate>Sat, 25 Apr 2026 00:54:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=47897617</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=47897617</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47897617</guid></item><item><title><![CDATA[Ask HN: Any recommendataions for exporting data from Amazon?]]></title><description><![CDATA[
<p>I was hoping that there would be an official API or MCP server for getting my own shopping/order history out of Amazon, but I'm not finding anything.  Has anyone solved this problem?<p>Context: I'm just trying to get more efficient with tax paperwork and household management.  An MCP server in which my agent could search for products (and examine the listings to see if they actually match my requirements, such as dietary restrictions) would be even more amazing, but that's probably asking too much.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47896789">https://news.ycombinator.com/item?id=47896789</a></p>
<p>Points: 13</p>
<p># Comments: 3</p>
]]></description><pubDate>Fri, 24 Apr 2026 22:52:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=47896789</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=47896789</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47896789</guid></item><item><title><![CDATA[Ask HN: How do you search the web programmatically these days?]]></title><description><![CDATA[
<p>For the first time in a long time, I need to query a search engine programmatically, and found that most of them block the use of curl, etc.<p>So, my question is simple: how do you solve the problem? I've tried searxng with mediocre success, but it seems a bit heavy to have to be running a complete separate service for this one thing that I only need every once in a while.  I haven't tried using a service that requires an API key, simply because I'm not sure which direction to go or who to go with.<p>Just thought I would ask here first.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47809373">https://news.ycombinator.com/item?id=47809373</a></p>
<p>Points: 6</p>
<p># Comments: 9</p>
]]></description><pubDate>Fri, 17 Apr 2026 19:02:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=47809373</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=47809373</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47809373</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Show HN: I made a website to write online math as fast as paper"]]></title><description><![CDATA[
<p>It would help to have some direction of what to do on the landing page.<p>Editing to give more context:<p>I'm on an ultrawide and didn't see the help at the top right corner.<p>But, now I'm thinking: "OK, I typed something... what do I do with it?"  Is the intent to copy/paste it somewhere?  Take a screenshot?  Does it convert to a less-savory format (e.g., latex)?  Just looking for some directions.<p>By the way... congrats on shipping a project!</p>
]]></description><pubDate>Sat, 28 Feb 2026 00:37:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=47188303</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=47188303</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47188303</guid></item><item><title><![CDATA[New comment by coreyp_1 in "A modern 35mm film scanner for home"]]></title><description><![CDATA[
<p>I gave up trying to read the article when animations started happening when I scrolled.  It's annoying and I have better things to do than waste time waiting for your animations to stutter and finish moving around when I'm trying to scan the article.  Good luck with whatever you're trying to do.</p>
]]></description><pubDate>Tue, 11 Nov 2025 21:16:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=45892974</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=45892974</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45892974</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Show HN: See chords as flags – Visual harmony of top composers on musescore"]]></title><description><![CDATA[
<p>Have you ever explored the idea of shaped notes?<p>There's multiple different approaches with both 4-shape and 7-shape systems being common.  But the point is that your color system seems largely correlated to it, and there has been research done on the shape note system.<p><a href="https://en.wikipedia.org/wiki/Shape_note" rel="nofollow">https://en.wikipedia.org/wiki/Shape_note</a></p>
]]></description><pubDate>Thu, 06 Nov 2025 19:26:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=45839207</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=45839207</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45839207</guid></item><item><title><![CDATA[New comment by coreyp_1 in "Pyrex catalog from from 1938 with hand-drawn lab glassware [pdf]"]]></title><description><![CDATA[
<p>I love the hand-drawn illustrations, but I really love the typography.<p>Does anyone know which fonts (or, probably more importantly, which modern-day equivalents) are used to get this feeling?</p>
]]></description><pubDate>Mon, 27 Oct 2025 15:48:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=45722342</link><dc:creator>coreyp_1</dc:creator><comments>https://news.ycombinator.com/item?id=45722342</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45722342</guid></item></channel></rss>