<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: geuis</title><link>https://news.ycombinator.com/user?id=geuis</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 11 Sep 2026 04:10:11 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=geuis" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by geuis in "OpenLogi"]]></title><description><![CDATA[
<p>Fast download for me. But immediately denied. Doesn't run on Mac intel hardware.</p>
]]></description><pubDate>Wed, 19 Aug 2026 05:42:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=49357326</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=49357326</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49357326</guid></item><item><title><![CDATA[New comment by geuis in "Ask HN: Who wants to be hired? (August 2026)"]]></title><description><![CDATA[
<p><p><pre><code>  Location: San Francisco
  Remote: Yes
  Willing to relocate: No
  Technologies: TypeScript/JS, React, node.js, Redis, Postgres, pgvector, LLM agents, Cloud (AWS/GCP/Azure), ci/cd pipelines, other tech
  Résumé/CV: on request
  Email: charles@geuis.com</code></pre></p>
]]></description><pubDate>Fri, 07 Aug 2026 03:25:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=49205591</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=49205591</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49205591</guid></item><item><title><![CDATA[New comment by geuis in "Cyberpunk Video Games"]]></title><description><![CDATA[
<p>Cyberpunk 2077:<p>> Gameplay Type: First Person Shooter Role Playing Game
Summary: A long anticipated release with eight years of development time, the game’s launch has been plagued with bugs and poor performance as well as decidedly mixed reviews. Regardless, the title offers gamers the largest open world cyberpunk universe thus far, so despite the rather uninspired art design and a plot that brings nothing new to the genre, this game is the best available to allow players to immerse themselves in a cyberpunk setting.<p>This is a very dated and seriously opinionated review.</p>
]]></description><pubDate>Tue, 04 Aug 2026 11:41:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=49167217</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=49167217</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49167217</guid></item><item><title><![CDATA[New comment by geuis in "LLM Honeypot"]]></title><description><![CDATA[
<p>Wonderful piece of art. Excellent callback to what the web used to look like when I was a teenager.</p>
]]></description><pubDate>Thu, 30 Jul 2026 01:06:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=49105017</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=49105017</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49105017</guid></item><item><title><![CDATA[New comment by geuis in "Show HN: I was tired of opening 2 tabs for every HN link, so I made a userscript"]]></title><description><![CDATA[
<p>I don't understand the problem space. Meaning I don't understand what this solves.<p>My use case, even on phone:<p>View HN<p>Right click link to open in new tab
OR: tap/hold a link then open I a new window.<p>What problem is this solving?</p>
]]></description><pubDate>Wed, 29 Jul 2026 03:01:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=49092948</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=49092948</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49092948</guid></item><item><title><![CDATA[New comment by geuis in "The new rules of context engineering for Claude 5 generation models"]]></title><description><![CDATA[
<p>Good question! I think I'll use that as a counter question next time I interview. Ask a technical member of the team I'm interviewing with how they handled that situation.</p>
]]></description><pubDate>Sun, 26 Jul 2026 01:17:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=49053629</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=49053629</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49053629</guid></item><item><title><![CDATA[New comment by geuis in "The new rules of context engineering for Claude 5 generation models"]]></title><description><![CDATA[
<p>I finally made progress today on a deeply intractable problem that Sonnet was just incapable of solving despite hours of experimentation and multiple attempts. I swapped over to Opus in a new handoff session with the expectation of using at least one 5 hour session. It wasn't quick and took several hours but eventually Opus dialed in on several cascading base failures resulting from how the base vision model was being converted to coreml. It eventually was able to provide a combination of conversion and Swift changes that semi fixed the issue but still didn't solve the core conversion issues.<p>Then since Anthropic was so kind to provide $100 for Fable credits, I did another handoff to let Fable attack the root issues again. Several more hours and I'm back to seeing the same issues again and Fable is wandering around trying different things. I'm down about $40 of free money and still don't have a solution.<p>This is where having the human engineer in the loop benefits from a deep understanding of the problem domain. In this case, I don't yet.<p>I know the high level architecture I'm building, but the deep specifics of how vision models work and how conversion across platforms should be done isn't something I know yet.<p>So I'm left learning as I go and relying on constant feedback with the models to provide what guidance I can while learning exactly what is being done.<p>Someone who already knows these architectures would likely be able to get to the solution much faster.</p>
]]></description><pubDate>Sun, 26 Jul 2026 00:49:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=49053467</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=49053467</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49053467</guid></item><item><title><![CDATA[New comment by geuis in "Tell HN: Namecheap gave my account to an unverified third party"]]></title><description><![CDATA[
<p>Glad you posted your experience. I'll definitely be keeping my eye out for shenanigans on my own domains.</p>
]]></description><pubDate>Thu, 23 Jul 2026 22:04:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=49028670</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=49028670</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49028670</guid></item><item><title><![CDATA[New comment by geuis in "Tell HN: Namecheap gave my account to an unverified third party"]]></title><description><![CDATA[
<p>I've been a long, long term customer of Namecheap as well.<p>Domain privacy protection is a feature that Namecheap provides for all valid domains. Its included by default at no extra cost.<p>The poster didn't indicate if they had this feature enabled or not for the domain. It would have prevented the college club person from even seeing their email address to initiate a password reset.<p>This clearly isn't an answer for NC's customer support personnel and company policies.<p>But I've been a happy customer for many years and I discourage others from immediately reading other comments and rushing to jump to other registrars without doing your due dilligence.<p>Remember that in any situation, the people most likely to leave negative comments and reviews are the people that have had genuine bad experiences or feel like they've been slighted, even if unwarranted.</p>
]]></description><pubDate>Thu, 23 Jul 2026 21:54:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=49028570</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=49028570</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49028570</guid></item><item><title><![CDATA[New comment by geuis in "Can a MUD evaluate LLMs? A $99 proof of concept"]]></title><description><![CDATA[
<p>They aren't all gone. E.g. this is a mud I've played on occasionally for the last 30 years: <a href="https://theforestsedge.com/" rel="nofollow">https://theforestsedge.com/</a></p>
]]></description><pubDate>Wed, 22 Jul 2026 21:26:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=49013685</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=49013685</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49013685</guid></item><item><title><![CDATA[New comment by geuis in "CO2 overload in blood suggests toxic atmosphere within 50 years"]]></title><description><![CDATA[
<p>No. Even with the amount of co2 current being dumped into the atmosphere there's not enough total solar energy capture to Venus things up. A few thousand years, absolutely.<p>To add: desertification and more or less removing the support systems for modern population levels can easily happen with what's going on. But the oceans won't boil first. Everything else will die first.</p>
]]></description><pubDate>Mon, 20 Jul 2026 00:39:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=48973114</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=48973114</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48973114</guid></item><item><title><![CDATA[New comment by geuis in "Bananas sprout in Rayleigh Garden UK after 15 years"]]></title><description><![CDATA[
<p>Lot of excellent information. Thanks. I'm glad someone out there doesn't have arachnophobia. I'm also glad it's not me.</p>
]]></description><pubDate>Sun, 19 Jul 2026 22:41:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=48972352</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=48972352</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48972352</guid></item><item><title><![CDATA[New comment by geuis in "Ask HN: Who wants to be hired? (July 2026)"]]></title><description><![CDATA[
<p><p><pre><code>  Location: San Francisco
  Remote: Yes
  Willing to relocate: No
  Technologies: TypeScript/JS, React, node.js, Redis, Postgres, pgvector, LLM agents, Cloud (AWS/GCP/Azure), ci/cd pipelines, other tech
  Résumé/CV: on request
  Email: charles@geuis.com</code></pre></p>
]]></description><pubDate>Wed, 01 Jul 2026 20:43:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=48752844</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=48752844</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48752844</guid></item><item><title><![CDATA[New comment by geuis in "An Introduction to YOLO26"]]></title><description><![CDATA[
<p>Doesn't work for my use-case. GroundingDINO is a text to bounding box model. SAM2 supports coordinate based masks (user taps or clicks somewhere in an image), which is what my research app needs.</p>
]]></description><pubDate>Tue, 23 Jun 2026 09:28:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=48642418</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=48642418</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48642418</guid></item><item><title><![CDATA[New comment by geuis in "An Introduction to YOLO26"]]></title><description><![CDATA[
<p>Was evaluating YOLO26 within the last month for its on-device (iPhone 16 Pro) segmentation capabilities. Its decent, but its biggest limitation is that its only trained on 80 COCO classes (meaning pre-labeled images). If whatever is in your images isn't in the 80 classes, its invisible to YOLO26. 
Conversely I have SAM2 running on-device and its my current workhorse. The biggest benefit with SAM2 for me is that it does fine-grained segmentation masks but isn't trained on labeled images. This was a specific requirement for the app I'm building. SAM2 isn't anywhere as speedy as the native Vision framework apis, but it is more capable across a vastly wider array of potential image targets.</p>
]]></description><pubDate>Tue, 23 Jun 2026 06:20:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=48641073</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=48641073</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48641073</guid></item><item><title><![CDATA[New comment by geuis in "The 100k Whys of AI"]]></title><description><![CDATA[
<p>Ignore me</p>
]]></description><pubDate>Sun, 21 Jun 2026 06:49:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=48616302</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=48616302</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48616302</guid></item><item><title><![CDATA[New comment by geuis in "How many of the 170k English words do you know?"]]></title><description><![CDATA[
<p>Guessing you've never worked a service job. It's a good way to learn how to interact with the public early on. The success model is not being fired for bad social customer interactions.<p>Even if you're an introvert, working for a couple months at Olive Garden when you're 19 helps you to smile and be polite when 80% of the customers are mouth breathing idiots. Turns out they aren't all mouth breathers and those para social skills come into play later during your career.<p>I highly support kids of all origins working in service for a bit. Ain't a class thing, but is very helpful in getting used to the breadth and depth of people.</p>
]]></description><pubDate>Sat, 20 Jun 2026 00:33:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=48605017</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=48605017</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48605017</guid></item><item><title><![CDATA[New comment by geuis in "How many of the 170k English words do you know?"]]></title><description><![CDATA[
<p>It's not fun because it isn't challenging. I have an expert-1 level of English as a native speaker and heavy reader. But absolutely nothing in this is challenging at all. The one question I got wrong was because the 4 proscribed answer options weren't specific enough. So overall there's no value in this.</p>
]]></description><pubDate>Sat, 20 Jun 2026 00:27:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=48604981</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=48604981</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48604981</guid></item><item><title><![CDATA[New comment by geuis in "How many of the 170k English words do you know?"]]></title><description><![CDATA[
<p>There are no hard words in this puzzle. This is all basic English.</p>
]]></description><pubDate>Sat, 20 Jun 2026 00:25:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=48604958</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=48604958</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48604958</guid></item><item><title><![CDATA[New comment by geuis in "How many of the 170k English words do you know?"]]></title><description><![CDATA[
<p>Not sure what this is measuring. I did 30-40 words and got bored because the words are really basic. There's no challenge here. Not even a fun 5 minute game. These are basic English words, nothing extraordinarily hard to understand.</p>
]]></description><pubDate>Sat, 20 Jun 2026 00:24:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=48604952</link><dc:creator>geuis</dc:creator><comments>https://news.ycombinator.com/item?id=48604952</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48604952</guid></item></channel></rss>