<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: jchook</title><link>https://news.ycombinator.com/user?id=jchook</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 08 Sep 2026 16:41:01 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=jchook" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by jchook in "Show HN: Wg-admin – web UI for an existing WireGuard host"]]></title><description><![CDATA[
<p>Seems like high-risk and low-reward for your network security. You could host it behind the WG interface, but… still exposing the castle’s master key to a python web app.<p>I have found that WG client management is as simple as a couple scripts and a TSV file to match pubkeys to users.<p>Anyhow, cool project and I like the overall concept of respecting existing config.</p>
]]></description><pubDate>Mon, 07 Sep 2026 22:08:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=49603503</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49603503</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49603503</guid></item><item><title><![CDATA[New comment by jchook in "Orbs"]]></title><description><![CDATA[
<p>I’ve used a few of the hosted VM options for this like Coder and really dislike having to do my work in a web browser.<p>This is why I made ParaSpace (<a href="https://paraspace.dev/" rel="nofollow">https://paraspace.dev/</a>)<p>With ParaSpace I can use a real terminal and my normal tooling to develop locally on fast booting isolated containers. I even get to bring my own dotfiles.</p>
]]></description><pubDate>Sun, 30 Aug 2026 16:55:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=49500394</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49500394</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49500394</guid></item><item><title><![CDATA[New comment by jchook in "The Twelve-Factor App (2025)"]]></title><description><![CDATA[
<p>You have to enjoy this article from the perception of its time.<p>For example #1, the idea of a central codebase + many deploys was not always the way folks did things lol.<p>The (2025) date must not be correct…</p>
]]></description><pubDate>Sat, 29 Aug 2026 06:32:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=49487492</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49487492</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49487492</guid></item><item><title><![CDATA[New comment by jchook in "U.S. sanctions against the A/I Collective"]]></title><description><![CDATA[
<p>I wonder why Epstein was communicating with 4chan's founder in 2011...</p>
]]></description><pubDate>Sat, 29 Aug 2026 03:02:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=49486514</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49486514</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49486514</guid></item><item><title><![CDATA[New comment by jchook in "Tell HN: US LLM models are smarter outside US working hours"]]></title><description><![CDATA[
<p>For sure Claude especially must have a knob that allows them to route traffic to lower quantizations as desired, as well as arbitrary throttling.<p>It’s clear as day. I’ve also noticed this behavior on Sundays, not just US workday hours.</p>
]]></description><pubDate>Fri, 21 Aug 2026 12:48:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=49387310</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49387310</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49387310</guid></item><item><title><![CDATA[New comment by jchook in "Vomit: Clean up Claude 5's token output with a separate LLM"]]></title><description><![CDATA[
<p>Claude already does summaries at the end of long output but they often sound even more like terse jargon nonsense than the long form, eg “the hardwired seam and the relocated barrel”.<p>Sometimes the summaries feel totally alien to the task or code.</p>
]]></description><pubDate>Thu, 20 Aug 2026 23:03:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=49381467</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49381467</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49381467</guid></item><item><title><![CDATA[New comment by jchook in "Qwen 3.8 27B"]]></title><description><![CDATA[
<p>After learning a little Mandarin I was amazed at how much simpler the Chinese grammar is than all Latin, Germanic, Romance, etc languages.<p>No gender, cases, tenses, conjugation, articles, word order inversion, etc. It's remarkable.<p>Mandarin has it's own complexities but grammar wise, it feels more optimized or simpler.</p>
]]></description><pubDate>Sat, 15 Aug 2026 09:30:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=49309098</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49309098</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49309098</guid></item><item><title><![CDATA[New comment by jchook in "DLLM: Minimal, clean coding agent built directly on llama.cpp without overhead"]]></title><description><![CDATA[
<p>Long live the D programming language!</p>
]]></description><pubDate>Wed, 12 Aug 2026 23:01:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=49279753</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49279753</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49279753</guid></item><item><title><![CDATA[Banner Depot 2000: archive web ad banners from 1990s and early 2000s]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.banner-depot-2000.net/">https://www.banner-depot-2000.net/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49279739">https://news.ycombinator.com/item?id=49279739</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 12 Aug 2026 23:00:02 +0000</pubDate><link>https://www.banner-depot-2000.net/</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49279739</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49279739</guid></item><item><title><![CDATA[New comment by jchook in "Go is an ideal language for AI-assisted software engineering"]]></title><description><![CDATA[
<p>Good point.<p>It's sometimes challenging to get a Rust program to compile... but if you do, it's probably going to work.</p>
]]></description><pubDate>Wed, 12 Aug 2026 05:38:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=49268189</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49268189</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49268189</guid></item><item><title><![CDATA[New comment by jchook in "How I use LLMs to learn complex topics"]]></title><description><![CDATA[
<p>This looks like the most convoluted and token heavy way to consume a bulleted list.</p>
]]></description><pubDate>Mon, 10 Aug 2026 04:35:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=49239227</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49239227</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49239227</guid></item><item><title><![CDATA[New comment by jchook in "Managing AI Coding Costs at Scale"]]></title><description><![CDATA[
<p>This is very close to my workflow but you forgot one important step:<p>- Suggest a better approach that makes the AI say, “That’s much simpler. And you’re right. My original plan was over-engineered.”</p>
]]></description><pubDate>Fri, 07 Aug 2026 20:17:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=49215702</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49215702</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49215702</guid></item><item><title><![CDATA[New comment by jchook in "Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac"]]></title><description><![CDATA[
<p>New macOS is bloatware that makes your computer slower</p>
]]></description><pubDate>Thu, 30 Jul 2026 04:26:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=49106121</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49106121</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49106121</guid></item><item><title><![CDATA[New comment by jchook in "Kill The Cookie Banner"]]></title><description><![CDATA[
<p>Obvious move is to modify GDPR to not be so obtuse.</p>
]]></description><pubDate>Mon, 27 Jul 2026 06:50:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=49065941</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49065941</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49065941</guid></item><item><title><![CDATA[New comment by jchook in "Kill The Cookie Banner"]]></title><description><![CDATA[
<p>The most frustrating thing about the cookie banner is that the solution was always obvious: just use the DNT setting on your browser (Do Not Track). It already existed.<p>However, powerful interest groups like ad companies that profit from your attention (which hysterically virtually powers the Internet today) were able to stop it from happening.<p>It was debated way back in 2009 when the GDPR was being developed. Iirc the argument was that browsers accept cookies by default so users do not get a fair consent moment. This is obviously easily fixed by regulation requiring browsers to ask users once.<p>Seems extremely backwards that we chose to forever darken the entire Web browsing experience just so users can "benefit" from a per-site option to let Google profit from them, with virtually zero payoff for the end user (ad relevance?).<p>P.S. If ad revenue is an essential pillar of Internet survival and fruition, the clear alternative seems to be sharing a fraction of that revenue with the tracked consumer.</p>
]]></description><pubDate>Sun, 26 Jul 2026 23:03:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=49063269</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49063269</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49063269</guid></item><item><title><![CDATA[New comment by jchook in "[dead]"]]></title><description><![CDATA[
<p>Can an AI slop plugin effectively make AI less sloppy?</p>
]]></description><pubDate>Sun, 26 Jul 2026 21:34:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=49062649</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=49062649</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49062649</guid></item><item><title><![CDATA[New comment by jchook in "Kimi K3: Open Frontier Intelligence"]]></title><description><![CDATA[
<p>Have a strong feeling that Anthropic solicited the ban from Lutnick as part of their, “so powerful it’s a national security threat” marketing campaign.<p>Pretty evident as they kicked it off with self-imposed limits (“0days on every OS”) etc, OpenAI didn’t get the same treatment, and the ban was conveniently lifted as soon as they needed to compete.</p>
]]></description><pubDate>Fri, 17 Jul 2026 14:37:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=48947908</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=48947908</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48947908</guid></item><item><title><![CDATA[New comment by jchook in "The git history command"]]></title><description><![CDATA[
<p>Obligatory git joke.<p>Git gets easier once you understand branches are homeomorphic endofunctors mapping submanifolds of a Hilbert space<p><a href="https://softwareengineering.stackexchange.com/questions/256450/are-git-branches-in-fact-homeomorphic-endofunctors-mapping-submanifolds-of-a" rel="nofollow">https://softwareengineering.stackexchange.com/questions/2564...</a></p>
]]></description><pubDate>Tue, 14 Jul 2026 12:18:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=48905633</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=48905633</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48905633</guid></item><item><title><![CDATA[New comment by jchook in "How to stop Claude from saying load-bearing"]]></title><description><![CDATA[
<p>SillyTavern folks have been perfecting the unslop solutions for years now.<p>Gotta be a way to draw from their progress.</p>
]]></description><pubDate>Tue, 14 Jul 2026 12:08:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=48905511</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=48905511</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48905511</guid></item><item><title><![CDATA[New comment by jchook in "Show HN: TokenDrift – find hardcoded colors/spacing hiding in your CSS"]]></title><description><![CDATA[
<p>I am curious about the false positives and why you would need a tool for this rather than just a clever prompt for an LLM.</p>
]]></description><pubDate>Mon, 13 Jul 2026 09:18:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=48889910</link><dc:creator>jchook</dc:creator><comments>https://news.ycombinator.com/item?id=48889910</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48889910</guid></item></channel></rss>