<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: x3haloed</title><link>https://news.ycombinator.com/user?id=x3haloed</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 18 Nov 2026 04:05:45 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=x3haloed" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by x3haloed in "GPT‑6.2 Astra and Sol"]]></title><description><![CDATA[
<p>Google ain’t in the same league right now.</p>
]]></description><pubDate>Tue, 17 Nov 2026 20:37:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=50537820</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50537820</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50537820</guid></item><item><title><![CDATA[New comment by x3haloed in "GPT‑6.2 Astra and Sol"]]></title><description><![CDATA[
<p>I miss 5.6-Sol’s attack dog nature. Everything in the 6 family just feels like it’s sleepy.</p>
]]></description><pubDate>Tue, 17 Nov 2026 20:32:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=50537765</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50537765</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50537765</guid></item><item><title><![CDATA[New comment by x3haloed in "We don't need more apps. We need better open source"]]></title><description><![CDATA[
<p>1. It's a stress on maintainers.
2. OS projects often close their doors to AI. See point #1.<p>The fact that free software is benefitting at all from more coding power is a win. We have bottlenecks to solve though.</p>
]]></description><pubDate>Tue, 17 Nov 2026 15:44:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=50532965</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50532965</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50532965</guid></item><item><title><![CDATA[New comment by x3haloed in "All AI-generated code should be Open Source"]]></title><description><![CDATA[
<p>Kind of a silly position. I mean, if it's you're code verbatim, then yeah, it's a violation. Shouldn't be allowed. But like... it saw open-source code and therefore all output must be open source? I don't know about that.<p>Here's where I can get on board. I think people should be putting AI to work to improve everyone's lives for free. Your version of "should" is like "we should make this a law." My version of "should" is more like a moral recommendation -- we <i>should</i> be using as much of our subscriptions as possible to benefit everyone instead of enriching a handful of people. I view it as a natural extension of the spirit of free software to begin with. Software <i>should</i> be free (as in freedom), and we finally have enough development power to make real headway on that.</p>
]]></description><pubDate>Sun, 15 Nov 2026 16:43:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=50508330</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50508330</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50508330</guid></item><item><title><![CDATA[New comment by x3haloed in "I'm not convinced the AI bubble exists"]]></title><description><![CDATA[
<p>This is the point. hmontazeri is imagining where AI still has left to grow as a consumer product, but AI is currently more of a business product. Even without a new consumer use case, it's easy to see demand for tokens keep going up.</p>
]]></description><pubDate>Mon, 09 Nov 2026 15:12:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=50426745</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50426745</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50426745</guid></item><item><title><![CDATA[New comment by x3haloed in "Flawless UI-UX Skill 1.0.0"]]></title><description><![CDATA[
<p>Here's the thing. As you're indicating, UI and UX are not the same thing, but they're both subjective.<p>You can ask the model to implement common patterns for both UI and UX. You can ask the model to correct obvious UI errors.<p>But you can't really ask the model to have UI taste unless you supply that taste, and you can't ask a model to "do UX" in a vacuum. UX work <i>requires</i> user testing. So any UX workflow that is going to be handled by agents must also include observational data of humans using the software.<p>There is no set of instructions that can do "UI/UX" without also incorporating human feedback.</p>
]]></description><pubDate>Fri, 06 Nov 2026 19:59:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=50397570</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50397570</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50397570</guid></item><item><title><![CDATA[New comment by x3haloed in "Tesla to wind down Cybertruck production"]]></title><description><![CDATA[
<p>I had a pre-order. The reason I canceled was because the delivered product had a lot less range and was much more expensive than previously announced.<p>There were other things that contributed to the decision, too: the announced "stressed skin" exoskeleton was panned in favor of adhering the body panels to the body with glue, it became clear that Tesla's profit and valuation were funding Elon's right-wing political project, and I would have preferred a solid-axle design.<p>The absurdity was not what was wrong with it. It's OK to be absurd. I really liked the stainless steel design. Less trail damage when off-roading and no need to worry about paint scratches causing body rust. The door wedge design? Meh. But it enabled the stainless steel body.<p>In the end, I want what the Cybertruck failed to deliver: a full-size electric pickup at a good price with excellent range. I currently have my eyes on the RAM REV. We'll see if that one gets axed, too.</p>
]]></description><pubDate>Fri, 06 Nov 2026 16:04:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=50394105</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50394105</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50394105</guid></item><item><title><![CDATA[New comment by x3haloed in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>Where do you find that T3 Code is strongest and where it is weakest?</p>
]]></description><pubDate>Wed, 04 Nov 2026 16:43:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=50368179</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50368179</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50368179</guid></item><item><title><![CDATA[New comment by x3haloed in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>I want to make a joke about that last line so badly.<p>I've had the same experience as you with Claude, and I have to choose a single subscription, so I'm on Codex. I definitely wish I had access to Opus 5.5 right now.</p>
]]></description><pubDate>Wed, 04 Nov 2026 16:28:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=50367947</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50367947</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50367947</guid></item><item><title><![CDATA[New comment by x3haloed in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>Codex (Pro x 1), no outside models, custom harness, custom orchestration, custom agent harness.<p>I avoided building anything custom until I had to, and I avoided adding more than a single agent until I had to.<p>My preferred way to use AI for coding has been to work closely with a single coding agent with the code open. That changed wth 5.6-Sol and a handful of skill files. I stopped needing to watch closely to keep it from fucking up the codebase. With the right request, that combination will get the job done 9/10 times.<p>That unlocked a new workflow: as soon as a change is requested, a coding agent reads it and gives me a PR. I want a complete proposed code change in front of my eyeballs by the time I open the change request myself.<p>So I have a custom solution in place to manage a handful of agents aligned with this workflow.<p>Custom solutions are so cheap and easy now... it's really hard to put up with solutions that are only <i>mostly</i> right for the job.</p>
]]></description><pubDate>Wed, 04 Nov 2026 16:23:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=50367866</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50367866</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50367866</guid></item><item><title><![CDATA[New comment by x3haloed in "Survival LLM: AI assistant and emergency library that runs on your own computer"]]></title><description><![CDATA[
<p>I literally just said that you should let the AI surface the information for you -- <i>not summarize or draw a conclusion for you</i>.</p>
]]></description><pubDate>Mon, 02 Nov 2026 16:27:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=50339258</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50339258</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50339258</guid></item><item><title><![CDATA[New comment by x3haloed in "Why are good developers so wary of agentic development?"]]></title><description><![CDATA[
<p>True. Although I generally find that to be rare.</p>
]]></description><pubDate>Mon, 02 Nov 2026 16:20:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=50339123</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50339123</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50339123</guid></item><item><title><![CDATA[New comment by x3haloed in "Last night an AI agent performed brain surgery on a mouse"]]></title><description><![CDATA[
<p>Yeah, I don't like the direction of any of this.</p>
]]></description><pubDate>Mon, 02 Nov 2026 16:15:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=50339023</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50339023</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50339023</guid></item><item><title><![CDATA[New comment by x3haloed in "Last night an AI agent performed brain surgery on a mouse"]]></title><description><![CDATA[
<p>Yeesh. Claude still does that? I haven't had that problem since GPT 5.</p>
]]></description><pubDate>Mon, 02 Nov 2026 16:14:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=50338996</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50338996</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50338996</guid></item><item><title><![CDATA[New comment by x3haloed in "Ask HN: Which TV do you recommend for privacy?"]]></title><description><![CDATA[
<p>Any TV that you want. Just don't connect it to a network. Why is this hard?</p>
]]></description><pubDate>Mon, 02 Nov 2026 15:51:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=50338534</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50338534</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50338534</guid></item><item><title><![CDATA[New comment by x3haloed in "Prospero: A new coding harness for a more civilized age"]]></title><description><![CDATA[
<p>OK, I like this in concept a LOT. I especially like that it's efficient and headless with an attachable GUI.<p>But I don't like how opinionated it is: "Therefore Prospero prime design principle: Never wait forever. Every operation has a deadline. This decision influences everything."<p>I respect that opinion, but I don't share it, and therefore an entire coding harness developed <i>around</i> that opinion is not helpful for me.</p>
]]></description><pubDate>Sat, 31 Oct 2026 18:01:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=50318391</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50318391</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50318391</guid></item><item><title><![CDATA[New comment by x3haloed in "Why are good developers so wary of agentic development?"]]></title><description><![CDATA[
<p>Oh, you are 100% correct about that.</p>
]]></description><pubDate>Thu, 29 Oct 2026 20:13:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=50295143</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50295143</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50295143</guid></item><item><title><![CDATA[New comment by x3haloed in "Why are good developers so wary of agentic development?"]]></title><description><![CDATA[
<p>I have a suspicion that eventually you won't have to be a developer to successfully create good software. I do think that familiarity with algorithm design will still help a lot. But ultimately, if your verification, testing, and observability regimes are good enough, the exact implementation shouldn't matter.</p>
]]></description><pubDate>Thu, 29 Oct 2026 17:25:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=50292748</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50292748</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50292748</guid></item><item><title><![CDATA[New comment by x3haloed in "Why are good developers so wary of agentic development?"]]></title><description><![CDATA[
<p>This is why, to me, it's more interesting to ask the question "how are good devs attaining outsized successes with AI" than "why are good developers wary of AI?"<p>Yes, there are real reasons to be careful, but that's already obvious to everyone in the field. The real gold is in discovering how successful devs are managing these risks while also retaining the benefits.</p>
]]></description><pubDate>Thu, 29 Oct 2026 17:15:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=50292558</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50292558</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50292558</guid></item><item><title><![CDATA[New comment by x3haloed in "Why are good developers so wary of agentic development?"]]></title><description><![CDATA[
<p>Honestly, I see good points in both of your comment sets.<p>But there really is a floor on how deeply a person can understand their own software. There has to be a "good enough" somewhere. As a C# dev, I can understand my entire codebase pretty deeply. And I've read enough of the .NET Core framework to understand some of the nuances of how a lot of the methods we rely on every day are implemented. But I've never once looked at the CIL that Roslyn has produced, and certainly not inspected the machine code that the runtime has compiled. I can't read or write Assembly. I don't really know anything about the x86 or ARM instruction sets. My understanding of the CPU is barely better than "it's transistors," and even lower than that, I have a vague awareness that neutrinos from space can flip bits and there are error correcting mechanisms for that, but I have no idea how they work. And yet, I'm able to write fast and reliable software.<p>There are super knowledgeable devs out there who pretty much DO understand the whole thing, but it's impossible to memorize every line of every version of framework that you're using or the unique alterations and upgrades to every piece of silicon that your program will run on, and as you guys pointed out, proprietary operating systems are basically completely opaque to our understanding.<p>So the question is really "where is the practical floor that you stand on?" And for me, personally, there is room for at least some areas of code at the application level that I'm OK with never having read myself.</p>
]]></description><pubDate>Thu, 29 Oct 2026 17:03:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=50292339</link><dc:creator>x3haloed</dc:creator><comments>https://news.ycombinator.com/item?id=50292339</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50292339</guid></item></channel></rss>