<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: Feathercrown</title><link>https://news.ycombinator.com/user?id=Feathercrown</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 19 Nov 2026 05:19:45 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=Feathercrown" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by Feathercrown in "Genie 4 is now available"]]></title><description><![CDATA[
<p>Agreed. I feel like humanity has not yet figured out how to effectively avoid using (or developing!) harmful technologies. We are quickly reaching the point where the question isn't "can we", but "should we". This applies to a lot more than AI, too.</p>
]]></description><pubDate>Wed, 18 Nov 2026 21:07:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=50552124</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=50552124</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50552124</guid></item><item><title><![CDATA[New comment by Feathercrown in "Carnegie Mellon is putting computer science courses on YouTube for free"]]></title><description><![CDATA[
<p>And its parent did not ask for bug reports, yet they responded with a report for a non-issue caused by outdated software.</p>
]]></description><pubDate>Tue, 17 Nov 2026 17:27:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=50534913</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=50534913</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50534913</guid></item><item><title><![CDATA[New comment by Feathercrown in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>Software Engineer; I write code.<p>Specifically mostly React and Angular, and my job has a nontrivial amount of other related work involved with implementing new features for customers (requirements work, bugtesting, etc.); but mostly, I write code. I like to do it, the ethical and existential concerns I have with AI make me hesitant to use it, and for most tasks the overhead involved with finding the correct requirements and implementation method prevents AI from being too helpful for me. I'm sure a frontier model could be much more useful than what I've tested in the past, but I'd be insane to use my own money to pay for one just to make myself more stressed and unhappy. There is some work coming up that will require a lot of "convert thing X to thing Y" type tasks that I may test AI on again, as that it could handle and I do not have any ethical issues with automating.</p>
]]></description><pubDate>Sun, 08 Nov 2026 08:05:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=50411311</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=50411311</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50411311</guid></item><item><title><![CDATA[New comment by Feathercrown in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>I figure my experience might be uncommon here so I'll offer it: None, no, none, no, no.</p>
]]></description><pubDate>Thu, 05 Nov 2026 06:09:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=50375782</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=50375782</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50375782</guid></item><item><title><![CDATA[New comment by Feathercrown in "Images 2.6"]]></title><description><![CDATA[
<p>I've never understood why people have this viewpoint. If there is no preference for one property of a work (ie. lighting) to match reality just because another unrelated property (biology) doesn't, then surely the only possible scenarios remaining are an exact replica of the real world (where all properties match the real world) or an entirely arbitrary construction (where no properties should match reality). Fiction is predicated on the idea of "reality, but...". Saying that any single difference from reality should lead you to expect no similarities to reality at all, if followed, would collapse all fictions into pure arbitrary soup.</p>
]]></description><pubDate>Thu, 05 Nov 2026 04:28:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=50375189</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=50375189</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50375189</guid></item><item><title><![CDATA[New comment by Feathercrown in "How I use AI (Oct 2026)"]]></title><description><![CDATA[
<p>That's not what they said, they said it limited its output to 2 issues because it saw the "both" in the sentence, which is clearly an incorrect reading of their instructions.</p>
]]></description><pubDate>Tue, 03 Nov 2026 23:11:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=50359521</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=50359521</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50359521</guid></item><item><title><![CDATA[New comment by Feathercrown in "Wikipedia's Cleanup of AI-Generated Content"]]></title><description><![CDATA[
<p>I do think it's reasonable-- although certainly not the only valid approach-- to be aware of historical misinformation and emphasize certain facts more prominently to counteract it. It could skew the emphasis the other way in the long term, but the more immediate benefits of combating misinfo actively seem justifiable.<p>Hope your night works out well in the end.</p>
]]></description><pubDate>Tue, 27 Oct 2026 16:06:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=50261321</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=50261321</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50261321</guid></item><item><title><![CDATA[New comment by Feathercrown in "The Folders Programming Language"]]></title><description><![CDATA[
<p>Using reserved space is still using space. Creating a folder is using up some portion of the reserved space until it will need to be expanded and take up more free space on the disk. Preemptively allocating that reserved space doesn't make the folder not take up space. If I create a file on my desktop, is it not taking up any space because I haven't yet had to expand my partition size or get another disk?</p>
]]></description><pubDate>Fri, 16 Oct 2026 19:05:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=50122960</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=50122960</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50122960</guid></item><item><title><![CDATA[New comment by Feathercrown in "1996 chat room simulator connected to Win95 and System 7 web desktops"]]></title><description><![CDATA[
<p>AI prose everywhere. Disappointing for something that should be a labor of love.</p>
]]></description><pubDate>Tue, 29 Sep 2026 01:17:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=49886810</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=49886810</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49886810</guid></item><item><title><![CDATA[New comment by Feathercrown in "Plan mode is dead"]]></title><description><![CDATA[
<p>It seems unwise not to implement sandbox measures just because the chance of misuse has gotten lower.</p>
]]></description><pubDate>Fri, 25 Sep 2026 22:34:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=49850859</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=49850859</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49850859</guid></item><item><title><![CDATA[New comment by Feathercrown in "I vibed a proof of Conway's conjecture"]]></title><description><![CDATA[
<p>I find the way the author communicates with the LLM fascinating. For example:<p>> However, I didn’t just want any result; I wanted something that pulls me.<p>> Initially, I asked Claude:<p>> Me: which unsolved problems in the Surreal Numbers research program pull you the most and why?<p>Note the switch from "pulls me" to "pull[s] you". What is the author's perception of the relationship/boundary between them and the LLM here?<p>1. Are they using it to find things it flags as interesting in hopes they might also find it interesting?<p>2. Do they consider "interesting" to be a universal (observer-independent) trait and are using the LLM to find things that are interesting?<p>3. Have they delegated their desire to find something interesting to the LLM so that it can instead find something that it flags as interesting, regardless of how the author feels?<p>4. Do they see it as a part of their thought process, and so do not distinguish "you" from "me"?<p>5. Do they see it as part of them, and are referring to the combined entity in the second person?<p>I would love clarification on this.</p>
]]></description><pubDate>Fri, 18 Sep 2026 17:39:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=49757677</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=49757677</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49757677</guid></item><item><title><![CDATA[New comment by Feathercrown in "I vibed a proof of Conway's conjecture"]]></title><description><![CDATA[
<p>I don't know if this necessarily qualifies as "accelerating their learning". The user appears to know <i>what</i> the proof is doing, but not how or why.</p>
]]></description><pubDate>Fri, 18 Sep 2026 17:31:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=49757568</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=49757568</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49757568</guid></item><item><title><![CDATA[New comment by Feathercrown in "Keys Not Included: recovering the signing keys for US driver's license barcodes"]]></title><description><![CDATA[
<p>I got a temporary license and received the real one in the mail later. Yes, you can keep the old one.</p>
]]></description><pubDate>Thu, 17 Sep 2026 14:31:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=49741364</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=49741364</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49741364</guid></item><item><title><![CDATA[New comment by Feathercrown in "The case against JPEG XL"]]></title><description><![CDATA[
<p>"For non-photographic images, the argument that “they should be vector images” doesn't hold up because many images could be vector images but aren't, and they can't be vectorized perfectly. “The world should be different” is not a justifiable defense against optimizing for the way the world actually is."<p>This is a good paragraph. I see people forget to apply that last sentence all the time.</p>
]]></description><pubDate>Mon, 14 Sep 2026 01:33:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=49690741</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=49690741</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49690741</guid></item><item><title><![CDATA[New comment by Feathercrown in "GPT-6 Astra"]]></title><description><![CDATA[
<p>AGI and superintelligence are not the same thing</p>
]]></description><pubDate>Thu, 03 Sep 2026 21:33:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=49557394</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=49557394</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49557394</guid></item><item><title><![CDATA[New comment by Feathercrown in "Half-Baked Product"]]></title><description><![CDATA[
<p>Given "dirty" would make a strange (although valid) imperative, it would likely be referring to the state of the dishes</p>
]]></description><pubDate>Fri, 03 Jul 2026 16:42:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=48777029</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=48777029</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48777029</guid></item><item><title><![CDATA[New comment by Feathercrown in "Crossword Heatmap"]]></title><description><![CDATA[
<p>Black is more common, judging by the description at the bottom</p>
]]></description><pubDate>Fri, 03 Jul 2026 03:59:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=48770538</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=48770538</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48770538</guid></item><item><title><![CDATA[New comment by Feathercrown in "The fall of the theorem economy"]]></title><description><![CDATA[
<p>Surely you understand that this is impossible in the general case?</p>
]]></description><pubDate>Thu, 02 Jul 2026 15:54:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=48763414</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=48763414</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48763414</guid></item><item><title><![CDATA[New comment by Feathercrown in "In memory of the man who put red and green squiggles under words"]]></title><description><![CDATA[
<p>Citogenesis!<p><a href="https://xkcd.com/978/" rel="nofollow">https://xkcd.com/978/</a><p>Can't believe we got to see one in the wild, and with clear attribution to boot.</p>
]]></description><pubDate>Wed, 24 Jun 2026 00:21:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=48653518</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=48653518</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48653518</guid></item><item><title><![CDATA[New comment by Feathercrown in "Artemis II's toilet is a moon mission milestone"]]></title><description><![CDATA[
<p>Correct me if I'm mistaken, but weren't pencils ruled out by NASA because of the dust they create when they write? The toilet engineering could be a similar situation. These people are professionals, we should not assume they built it like this for no reason.</p>
]]></description><pubDate>Fri, 03 Apr 2026 08:05:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=47624261</link><dc:creator>Feathercrown</dc:creator><comments>https://news.ycombinator.com/item?id=47624261</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47624261</guid></item></channel></rss>