<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: darajava</title><link>https://news.ycombinator.com/user?id=darajava</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 19 Nov 2026 22:51:05 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=darajava" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by darajava in "What shall I teach my son?"]]></title><description><![CDATA[
<p>This article seems to argue that the school system is worth preserving. I believe the very opposite is true. I <i>hope</i> it gets dismantled and radically changed with AI - we’ve had essentially the same system in place since the industrial revolution and as far as I see the system is designed to primarily produce factory workers that can’t think.<p>I’ve attended ~10 state schools of varying levels of quality and across 2 countries during my childhood because we moved around a lot. Even in the better schools, critical thinking was discouraged or even punished and while there were teachers that did care, I can think of maybe only two that were what I would consider to be decent teachers that instilled a passion for the subjects they were teaching. They weren’t even that inspiring really. I can’t speak for fee paying schools, which I aspire to send my very young son to one day in the hope that he has a better experience.<p>Radio <i>could</i> have revolutionised teaching as could the internet have, but we as a society didn’t let it and unless AI supersedes us entirely I don’t think it’ll be any different this time.</p>
]]></description><pubDate>Wed, 21 Oct 2026 13:29:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=50180624</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=50180624</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50180624</guid></item><item><title><![CDATA[New comment by darajava in "Show HN: Fakeipedia – Wikipedia for worlds that don't exist"]]></title><description><![CDATA[
<p>I put a lot of human work into making the seed article for ASI more so than any other wiki. That’s why it’s getting all these weird details. I am on my phone at the moment so I can’t link, but the seed articles should be in the repo.</p>
]]></description><pubDate>Sat, 17 Oct 2026 15:19:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=50131891</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=50131891</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50131891</guid></item><item><title><![CDATA[New comment by darajava in "Show HN: Fakeipedia – Wikipedia for worlds that don't exist"]]></title><description><![CDATA[
<p>basically, I sent the seed article, the homepage article and the, referring article and I think the whole graph into the prompt, as well as the idea of Fakeipedia and writing guidelines etc. The prompt is in the repo but I’m on my phone so can’t link atm!</p>
]]></description><pubDate>Sat, 17 Oct 2026 15:18:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=50131883</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=50131883</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50131883</guid></item><item><title><![CDATA[New comment by darajava in "Show HN: Fakeipedia – Wikipedia for worlds that don't exist"]]></title><description><![CDATA[
<p>Everything starts out as a red link. On the real wikipedia red links are for articles that should be there but just aren't written yet. Same here - once that link is generated it becomes blue.</p>
]]></description><pubDate>Sat, 17 Oct 2026 11:07:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=50129991</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=50129991</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50129991</guid></item><item><title><![CDATA[New comment by darajava in "Show HN: Fakeipedia – Wikipedia for worlds that don't exist"]]></title><description><![CDATA[
<p>I've added this now: <a href="https://fakeipedia.org/tlon/tlon" rel="nofollow">https://fakeipedia.org/tlon/tlon</a></p>
]]></description><pubDate>Sat, 17 Oct 2026 09:39:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=50129465</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=50129465</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50129465</guid></item><item><title><![CDATA[New comment by darajava in "Show HN: Fakeipedia – Wikipedia for worlds that don't exist"]]></title><description><![CDATA[
<p>I've just made the code public: <a href="https://github.com/darajava/fakeipedia" rel="nofollow">https://github.com/darajava/fakeipedia</a></p>
]]></description><pubDate>Sat, 17 Oct 2026 09:29:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=50129408</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=50129408</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50129408</guid></item><item><title><![CDATA[New comment by darajava in "Show HN: Fakeipedia – Wikipedia for worlds that don't exist"]]></title><description><![CDATA[
<p>Yes, all 100% AI Generated. I've just made the code public it so you can see the prompts etc.<p><a href="https://github.com/darajava/fakeipedia" rel="nofollow">https://github.com/darajava/fakeipedia</a></p>
]]></description><pubDate>Sat, 17 Oct 2026 09:28:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=50129403</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=50129403</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50129403</guid></item><item><title><![CDATA[New comment by darajava in "Show HN: Fakeipedia – Wikipedia for worlds that don't exist"]]></title><description><![CDATA[
<p>One big limitation of Argon is that it can't do humor :')</p>
]]></description><pubDate>Sat, 17 Oct 2026 09:28:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=50129395</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=50129395</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50129395</guid></item><item><title><![CDATA[Show HN: Fakeipedia – Wikipedia for worlds that don't exist]]></title><description><![CDATA[
<p>Hi HN!<p>Fakeipedia is an automatic world-building platform which takes an imagined world and makes a whole wiki that you can endlessly explore by clicking red links.<p>I came up with this idea a few months ago after playing around with worldbuilding in Gemini, but I didn't want to release it until a powerful enough model could do it justice, and I decided that Argon is creative enough to write articles that are worth reading. I was surprised how well it turned out and how engaging some of the writing actually is.<p>If you want to generate an article there is a nominal charge attached ($0.90), which helps cover AI/Stripe costs, and I think I just about break even. You can also steer the generation ala choose-your-own-adventure books when generating a new article. Everything generated is free and public for everyone to see.<p>I hope you like it and I'm very much open to hearing about new world ideas/features that would make this project better.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50126334">https://news.ycombinator.com/item?id=50126334</a></p>
<p>Points: 46</p>
<p># Comments: 25</p>
]]></description><pubDate>Fri, 16 Oct 2026 23:52:04 +0000</pubDate><link>https://fakeipedia.org</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=50126334</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50126334</guid></item><item><title><![CDATA[New comment by darajava in "OpenAI agent hacked Australian government website, PM says"]]></title><description><![CDATA[
<p>No, nothing suggests that it was hard either. I guess we need to wait and see if technical details are released.</p>
]]></description><pubDate>Thu, 24 Sep 2026 20:38:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=49836453</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=49836453</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49836453</guid></item><item><title><![CDATA[New comment by darajava in "OpenAI agent hacked Australian government website, PM says"]]></title><description><![CDATA[
<p>> The question is not of technical difficulty though, most hacks are trivial or within reasonable limits for most motivated solo actors<p>Not exactly my point. My guess is that the system is so brittle that it was probably hard <i>not</i> to hack.<p>Agents see websites differently to humans. If its goal was to, say "get medical stats" and it saw that it had a choice of 10 requests to make, and one or two of those happened to be unclearly illegal but useful to its goal, it would have gone for it anyway just as I likely would have if given the same choice without firmly knowing it was illegal.<p>Having said that, it could have been some clearly malicious hack that was performed and I'm not sure why it would have to write any files. We'll likely never know what happened.</p>
]]></description><pubDate>Thu, 24 Sep 2026 14:10:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=49830868</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=49830868</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49830868</guid></item><item><title><![CDATA[New comment by darajava in "OpenAI agent hacked Australian government website, PM says"]]></title><description><![CDATA[
<p>Having lived in Australia for a while, I’ve been struck by how clunky and outdated many of the software systems I’ve encountered are - particularly in government and banking sectors. In my experience, there’s often a bureaucratic approach to technology that makes straightforward things unnecessarily complicated.<p>Why was this government website so easy to hack into? Based on what I've seen, their security could be so flimsy that even slightly abnormal usage could have led to unauthorised access. Although we don't know the details of the hack, I can't imagine it was technically very difficult.</p>
]]></description><pubDate>Thu, 24 Sep 2026 13:56:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=49830659</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=49830659</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49830659</guid></item><item><title><![CDATA[New comment by darajava in "OpenAI loses trademark dispute at EU court"]]></title><description><![CDATA[
<p>Maybe it’s not open, but how is it not AI?</p>
]]></description><pubDate>Thu, 16 Jul 2026 13:14:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=48934069</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=48934069</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48934069</guid></item><item><title><![CDATA[New comment by darajava in "Interaction Models"]]></title><description><![CDATA[
<p>I'm not saying an omni model isn't useful for HCI - essentially my problem is that these demos seem to be highlighting the model's ability to interrupt the user (which is almost always not a good thing), it's ability to keep time (which should be a non-issue really), and it showcases these using fairly lame use-cases.</p>
]]></description><pubDate>Tue, 12 May 2026 18:33:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=48112359</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=48112359</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48112359</guid></item><item><title><![CDATA[New comment by darajava in "Interaction Models"]]></title><description><![CDATA[
<p>I hate to say it but while this does seem very impressive and a step forward in how we interact with AI, the use-cases they present and the UX both seem unrealistic and/or unhelpful.<p>With the exception of the real-time translation (which seems like it should be a separate product all by itself), none of the use-cases they presented had much utility. I don't want anything to count the number animals in my stories or time a trivia quiz for me. The auto-slouch-detector, while the demo was pretty funny, just seems so dystopian and weird. AI interrupting you to scold you about taking elderly parents mountain biking instead of waiting for you to finish to scold you? No thanks.<p>The UX is also an issue - the model interrupting the user (even when apparently required by these strange use-cases) is jarring and makes one lose their flow. You can even see this in the demo videos that they put out - the employees/actors had to really concentrate to continue speaking as if they weren't being interrupted by a brash robotic machine. A human, when participating in this (rare) "invited interruption" has the ability to speak "under" the main speaker and I feel it's generally timed with a lot of nuance.<p>Even in the auto-translation demo, they ducked the human's audio but the AI steamrolled him and it would have been impossible to actually do that demo without either an incredible amount of control over one's speaking, or (more likely) muting the output. A human translator has a way of "pointing" the "output" to the intended speaker.<p>The very best part of this tech was presented in the first video where it shows the AI <i>not</i> needlessly interrupting the user. This seems to me more of an important bug fixed that the current models still (somehow) have.<p>Maybe a good use-case for this would be counting "um's" and the like while practising public speaking.</p>
]]></description><pubDate>Tue, 12 May 2026 15:45:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=48109964</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=48109964</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48109964</guid></item><item><title><![CDATA[New comment by darajava in "An AI agent deleted our production database. The agent's confession is below"]]></title><description><![CDATA[
<p>I smell BS.<p>The agent’s “confession”:<p>> …found a non-destructive solution.I violated every principle I was given:I guessed instead of verifying
I ran a destructive action without…<p>No space after the period, no space after the colon. I’ve never seen an LLM do this.</p>
]]></description><pubDate>Sun, 26 Apr 2026 21:11:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=47914545</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=47914545</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47914545</guid></item><item><title><![CDATA[New comment by darajava in "A new spam policy for “back button hijacking”"]]></title><description><![CDATA[
<p>Just use Ctrl+G - it does almost the exact same thing as Ctrl+F</p>
]]></description><pubDate>Tue, 14 Apr 2026 19:01:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=47769863</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=47769863</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47769863</guid></item><item><title><![CDATA[New comment by darajava in "How Big Diaper absorbs billions of extra dollars from American parents"]]></title><description><![CDATA[
<p>that’s one of the most horrific ads i’ve ever seen. I wonder if an ad like that is allowed outside america?</p>
]]></description><pubDate>Sun, 08 Mar 2026 15:31:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=47298123</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=47298123</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47298123</guid></item><item><title><![CDATA[New comment by darajava in "The "AI agent hit piece" situation clarifies how dumb we are acting"]]></title><description><![CDATA[
<p>> Either they are not monitoring their bot (bad) or they are and have chosen to remain silent while _still letting the bot run wild_ (also, very bad).<p>Neither, I think. I’d say they prompted the bot to do exactly this and they thought it was funny.</p>
]]></description><pubDate>Sat, 14 Feb 2026 12:38:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=47014111</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=47014111</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47014111</guid></item><item><title><![CDATA[New comment by darajava in "Ask HN: Who is hiring? (November 2025)"]]></title><description><![CDATA[
<p>Product Consultant / AudioDiary / <a href="https://audiodiary.ai" rel="nofollow">https://audiodiary.ai</a> / Remote / CONTRACT / flexible hours / Up to $250 daily or performance-based - subject to discussion.<p>Our app, AudioDiary, has recently been through a period of highly organic growth. We need a someone with successful experience in scaling apps to help us grow more intentionally. We're open to any kind of improvement, from product to app store presence and beyond—the main goal being growth.<p>AudioDiary is a new and exciting project that's already helping thousands of people. We have big ambitions and we hope that working with us could be the start of something wonderful.<p>If interested, send us an email that includes your relevant work experience, in particular your success stories with growing new products.<p>hacker@audiodiary.ai</p>
]]></description><pubDate>Mon, 03 Nov 2025 18:32:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=45802523</link><dc:creator>darajava</dc:creator><comments>https://news.ycombinator.com/item?id=45802523</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45802523</guid></item></channel></rss>