<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: plaguuuuuu</title><link>https://news.ycombinator.com/user?id=plaguuuuuu</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 24 May 2026 22:26:00 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=plaguuuuuu" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by plaguuuuuu in "We've made the world too complicated"]]></title><description><![CDATA[
<p>Also worth reading, especially today in LLM age: Simulacra and Simulation by Beaudrillard. Heavily inspired The Matrix. Although unlike the movie, he saw simulacra as irreversibly replacing reality, ie you can't get out of the matrix.</p>
]]></description><pubDate>Sun, 17 May 2026 13:42:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=48168857</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=48168857</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48168857</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "Frontier AI has broken the open CTF format"]]></title><description><![CDATA[
<p>you could try<p>* googling "CTF security"<p>* asking literally any AI to explain the article<p>Yes, you must beg. If you don't know what a CTF is, and <i>don't want to find out</i>, why read the article anyway</p>
]]></description><pubDate>Sun, 17 May 2026 09:07:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=48167241</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=48167241</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48167241</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "Ontario auditors find doctors' AI note takers routinely blow basic facts"]]></title><description><![CDATA[
<p>I don't think it's that hard to get them to say "I don't know"<p>I'm pretty sure they are actively trained to avoid it.<p>Besides, like, what would <i>you</i> do if you asked your $200/mo AI something and it blanked on you?</p>
]]></description><pubDate>Fri, 15 May 2026 08:23:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=48145957</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=48145957</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48145957</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "MacBook Neo and how the iPad should be"]]></title><description><![CDATA[
<p>Instead of doing creative work on the iPad, it should really be used as an input device for the mac.</p>
]]></description><pubDate>Sat, 25 Apr 2026 07:32:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=47899498</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47899498</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47899498</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "Technical, cognitive, and intent debt"]]></title><description><![CDATA[
<p>"Coding style should reflect the casual minimalism of expert programmers" used to to bump it up a bit, I guess it had the right activations or whatever, but I haven't bothered as much with this stuff with recent models cause (a) writing "You are a gigachad developer who is a Level 99 Staff Wizard at FAANG" doesn't work any more and (b) More or less they code like what they can see in their context; if you have a shit codebase you're going to get more shit, so theoretically I'd give a baseline coding style in some instructions, but realistically I haven't have enough motivation to bother with the last thingy I was working on.</p>
]]></description><pubDate>Thu, 23 Apr 2026 16:05:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=47877430</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47877430</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47877430</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "Technical, cognitive, and intent debt"]]></title><description><![CDATA[
<p>I've recently had the interesting experience of working on a Clean Architecture project for the first time. Pre and post-LLM adoption.<p>It has been... difficult. Services/modules organised by infrastructural layer rather than by feature. A mediator pattern abstracted away the handling of commands. Just in case one day you needed CreateFooCommand to be executed by a different handler, or something, I dunno. It was so hard to figure out how to navigate everything. And it felt like the entire tradeoff was for the purpose of stopping smoothbrains from adding the ORM to an API endpoint - but with the cost of this crushing accidental complexity that made it hard for <i>everyone</i> to hold everything in their heads, not just for me but also for the smart guys on the team.<p>It turns out that the LLMs also performed extremely poorly. All the heavy abstractions were too hard for them (not to mention most of the developers).<p>I knew I had no chance of shifting things away from that paradigm. But as luck would have it... we started basically vibe-rewriting it from scratch without bullshit enterprisey crap and its (a) dead simple (b) has most of the features after <i>one month</i> (c) even though the code is questionable, inelegant AI slop, with nearly <i>zero</i> regard to proper architectural design, <i>it's way easier to deal with than before</i><p>I've never felt so vindicated.</p>
]]></description><pubDate>Thu, 23 Apr 2026 15:57:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=47877330</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47877330</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47877330</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "Ping-pong robot beats top-level human players"]]></title><description><![CDATA[
<p>I'll carry an ammo belt of little EMP devices.</p>
]]></description><pubDate>Thu, 23 Apr 2026 09:12:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=47873649</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47873649</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47873649</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "A type-safe, realtime collaborative Graph Database in a CRDT"]]></title><description><![CDATA[
<p>im pretty sure gastown (the Beads part) stores tasks/memories/whatever in a DAG but I haven't looked into it in detail</p>
]]></description><pubDate>Tue, 21 Apr 2026 13:49:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=47848796</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47848796</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47848796</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "CEOs admit AI had no impact on employment or productivity"]]></title><description><![CDATA[
<p>I've always held the view that successfully using AI requires more knowledge and skill, as the burst radius of poor engineering decisions or lack of domain knowledge is <i>way</i> larger.<p>I just <i>cannot</i> see WITCH doing this without exponentiating the usual problems with outsourcing. I've seen some horrors. Can't wait for contractors wielding unprecedented chaos.</p>
]]></description><pubDate>Mon, 20 Apr 2026 07:52:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=47831454</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47831454</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47831454</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "Anonymous request-token comparisons from Opus 4.6 and Opus 4.7"]]></title><description><![CDATA[
<p>no way, I didn't realise this worked.<p>My attention span is such that I get side tracked and wind up taking longer than 5 mins quite a bit :D</p>
]]></description><pubDate>Sun, 19 Apr 2026 02:42:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=47821394</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47821394</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47821394</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "The buns in McDonald's Japan's burger photos are all slightly askew"]]></title><description><![CDATA[
<p>I'm only 50/50 but I swear they have only one app for the entire globe.<p>Can you imagine how complex that must be vs just making like 100 different apps in each country.<p>But eCoNoMiEs oF sCaLe<p>If you're balking at makin 100 different apps, then for reference, I am pretty sure my local mcdonalds - <i>just the one restaurant</i> turns over >10 mill a year, so you get a sense of how much they'd want to invest in, idk, the ordering front-end of every maccas in Australia</p>
]]></description><pubDate>Thu, 16 Apr 2026 01:47:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=47787696</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47787696</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47787696</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "Artemis II crew take “spectacular” image of Earth"]]></title><description><![CDATA[
<p>or sticky-tape it to the window.<p>d5 has an actual shutter yeah? not mirrorless? I think the shutter moving will spin the camera.</p>
]]></description><pubDate>Sat, 04 Apr 2026 00:45:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=47634321</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47634321</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47634321</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "OpenAI Acquires TBPN"]]></title><description><![CDATA[
<p>guarantee one of them caught an OpenAI guy murdering a prostitute or something</p>
]]></description><pubDate>Thu, 02 Apr 2026 22:38:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=47621116</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47621116</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47621116</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "OpenAI Acquires TBPN"]]></title><description><![CDATA[
<p>what do you even do on X, you basically just subscribe to a bunch of blowhards to get insider sloppy seconds, then occasionally yell into the void and hope someone (anyone) finally responds?</p>
]]></description><pubDate>Thu, 02 Apr 2026 22:37:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=47621096</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47621096</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47621096</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "Artemis II is not safe to fly"]]></title><description><![CDATA[
<p>too labor intensive - each launch already costs like $1bn, how bad can it be</p>
]]></description><pubDate>Tue, 31 Mar 2026 07:33:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=47583926</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47583926</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47583926</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "Six Math Essentials"]]></title><description><![CDATA[
<p>I don't think a <i>popular audience</i> is buying a book on mathematics.<p>But, the world is <i>huge</i>. Even if this is kind of niche (people who didn't really get into maths in school or college, but now have a strange impulse to pick it up for shits and giggles) the audience is still thousands of people. Or just, people who want to see how Tao connects everything up, because the way he sees and explains stuff is amazing.<p>There are levels to what's worth publishing or working on in general. Hardly <i>anyone</i> is going to be the next Steven Hawking but this obsession with the most popular or successful celebrity creators ultimately leads to this highly homogenised global media landscape. The most exciting thing about the internet for me was always accessing the long tail of truly unusual shit that you wouldn't find in book/record stores, tv, etc.</p>
]]></description><pubDate>Mon, 23 Feb 2026 04:58:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=47118314</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47118314</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47118314</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "Music Discovery"]]></title><description><![CDATA[
<p>the "you might also like" for a given artist is usually the most generic related artists - for anything remotely related you'll get basically the same list which is the middle of the venn diagram of everyone who listens to them</p>
]]></description><pubDate>Mon, 23 Feb 2026 01:24:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=47116881</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47116881</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47116881</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "Claude Sonnet 4.6"]]></title><description><![CDATA[
<p>even if you limit to 2/3 I think any sort of persistence that can be picked up by agents with the other 1 can lead to compromise, like a stored XSS.</p>
]]></description><pubDate>Tue, 17 Feb 2026 22:07:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=47054094</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=47054094</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47054094</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "Beyond agentic coding"]]></title><description><![CDATA[
<p>At work we use Clean Architecture which is <i>incredibly</i> hard to browse, even though I've been there for 6+ months now and know where everything is, I have to use so much working memory to gather together the files for a feature slice (endpoint, command, command handler, etc).<p>I've thought for a while of building this exact thing as a vscode extension because of how utterly shit it is :D<p>I really want the source code!</p>
]]></description><pubDate>Sun, 08 Feb 2026 10:52:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=46933183</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=46933183</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46933183</guid></item><item><title><![CDATA[New comment by plaguuuuuu in "Case study: Creative math – How AI fakes proofs"]]></title><description><![CDATA[
<p>Think of the lengthy prompt as being like a safe combination, if you turn all the dials in juuust the right way, then the model's context reaches an internal state that biases it towards different outputs.<p>I don't know how well this specific prompt works - I don't see benchmarks - but prompting is a black art, so I wouldn't be surprised at all if it excels more than a blank slate in some specific category of tasks.</p>
]]></description><pubDate>Mon, 26 Jan 2026 02:24:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=46761126</link><dc:creator>plaguuuuuu</dc:creator><comments>https://news.ycombinator.com/item?id=46761126</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46761126</guid></item></channel></rss>