<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: sfn42</title><link>https://news.ycombinator.com/user?id=sfn42</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 20 Jun 2026 14:41:52 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=sfn42" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by sfn42 in "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"]]></title><description><![CDATA[
<p>The thing about this is that you can choose how high level you go.<p>For example you can just tell it to make a website for a business with a webshop and it'll just generate thousands of lines of code and you have no control over anything. Or you can spend hours/days writing the specification and then have it generate it.<p>Or you can do what I do and work iteratively one feature at a time making sure everything is exactly the way you want it. I generally solve the problem myself then tell it what to do, or if I'm not sure what the best solution is I might discuss with the AI until we agree on a plan and then have it execute it. Often this leads to me learning useful things, like it will suggest a tool/feature that I didn't know about that's perfect for my usecase or it will identify a problem in my plan that I wouldn't have found until after spending hours on the implementation.<p>I've always been very detail oriented and I care a lot about code quality, I want my solutions to be clean, consistent and as simple as possible while solving the problem. To me, AI tools let me do that more quickly and better, it's not a compromise it's just flat out better in every dimension. It's about how you use it.<p>A lot of people seem to think that it's a binary choice, either hand craft a high quality bespoke solution or just vibe code a pile of trash. There's a whole spectrum in between those two, and I think there's a sweet spot where you still maintain control and understanding, it's just much faster and the result is actually better because it's not just you and the knowledge in your brain it's also the AI that practically knows everything - it will teach you things and suggest solutions you wouldn't have thought about, it makes you a better developer. It's a force multiplier and the smarter you are the better you will be at using it.<p>It's not a replacement it's an enhancement. It's like imagine a developer with Google vs one without, obviously the one with Google will be better because they have access to more information. The AI is like automatic google that just googles everything all the time, things you wouldn't have even thought to Google or things you couldn't possibly formulate a good search term for. With AI you can just show it a screenshot or describe an issue in detail and get a really solid answer a lot of the time. It's like having an expert on standby all the time, sure it's sometimes wrong but most of the time it's not and if you're smart you'll recognize when it isn't.<p>I'd say anyone who isn't using AI today aren't using their full potential. I don't see how anyone could possibly perform better without this tool than with it. I do see how someone who doesn't care could produce a lot of slop, but the people who refuse to use it aren't that guy. That guy has been using it to produce slop for years already. You can use it to produce top quality code if you choose to.</p>
]]></description><pubDate>Tue, 16 Jun 2026 10:59:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=48553328</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48553328</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48553328</guid></item><item><title><![CDATA[New comment by sfn42 in "Your ePub Is fine"]]></title><description><![CDATA[
<p>Yeah but we were kids, we didn't give a shit about any of that. Kind of still don't give a shit about any of it tbh. There's security holes in everything anyway.</p>
]]></description><pubDate>Mon, 15 Jun 2026 09:04:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=48538558</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48538558</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48538558</guid></item><item><title><![CDATA[New comment by sfn42 in "Your ePub Is fine"]]></title><description><![CDATA[
<p>Sounds like you didn't experience all the awesome flash games and animated videos etc that people made.</p>
]]></description><pubDate>Mon, 15 Jun 2026 08:42:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=48538375</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48538375</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48538375</guid></item><item><title><![CDATA[New comment by sfn42 in "No, everyone is not using AI for everything"]]></title><description><![CDATA[
<p>Come talk to me when it <i>isn't</i> an issue.</p>
]]></description><pubDate>Sun, 14 Jun 2026 16:27:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=48529111</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48529111</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48529111</guid></item><item><title><![CDATA[New comment by sfn42 in "Nobody ever gets credit for fixing problems that never happened (2001) [pdf]"]]></title><description><![CDATA[
<p>I just do my job to the best of my ability. I have to change jobs every couple years anyway to get proper pay bumps, so I don't really care what the higher ups think of me. The people near me are who I'll use as references and they generally know I'm great at what I do.</p>
]]></description><pubDate>Fri, 12 Jun 2026 07:01:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=48500773</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48500773</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48500773</guid></item><item><title><![CDATA[New comment by sfn42 in "CSS: Unavoidable Bad Parts"]]></title><description><![CDATA[
<p>My experience working with other peoples code is that they often use too many wrappers. I don't mind using some wrappers, often they're just necessary. But I'll often see components with like 4+ nested divs where half of them or more can just be removed with no visual change.  Not to mention spans, some people just use spans for everything, it's all divs and spans.<p>Personally I like to try to use semantic HTML where possible, as it helps with a11y and is nicer to read and work with. But I don't mind using some container/wrapper divs to make things look right.</p>
]]></description><pubDate>Thu, 11 Jun 2026 06:52:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=48487128</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48487128</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48487128</guid></item><item><title><![CDATA[New comment by sfn42 in "What it feels like to work with Mythos"]]></title><description><![CDATA[
<p>This has been a debate for ever, long before LLMs. On the one hand you have people who don't care, on the other you have people who produce good code.<p>Doesn't matter how fast you can make the wrong thing.</p>
]]></description><pubDate>Wed, 10 Jun 2026 13:30:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=48476025</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48476025</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48476025</guid></item><item><title><![CDATA[New comment by sfn42 in "Solar Energy Saves Europeans $135M a Day"]]></title><description><![CDATA[
<p>There's this thing called the power grid, it transports electricity across great distances.<p>And everything you're talking about is an issue with any kind of production, I don't know why you're bringing it up as if it's unique to solar. If you're building a factory that needs high amounts of stable power then you plan accordingly. Doesn't change the fact that solar is a useful way to generate electricity. I don't think anyone is saying we have to use it exclusively. We can use different solutions for different problems.</p>
]]></description><pubDate>Wed, 10 Jun 2026 00:55:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=48469861</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48469861</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48469861</guid></item><item><title><![CDATA[New comment by sfn42 in "Solar Energy Saves Europeans $135M a Day"]]></title><description><![CDATA[
<p>Across a large enough area it's always sunny somewhere. And clouds don't interfere as much as you'd think. Add in wind, hydro, nuclear and some gas and you can handle pretty much anything just fine.</p>
]]></description><pubDate>Tue, 09 Jun 2026 16:00:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=48462832</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48462832</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48462832</guid></item><item><title><![CDATA[New comment by sfn42 in "Uber's $1,500/month AI limit is a useful signal for AI tool pricing"]]></title><description><![CDATA[
<p>You're just expecting too much. If a task takes you 30 seconds to do you're almost certainly better off doing it yourself than getting an LLM to do it. If it's a recurring task it might make sense to create a skill for it, and this is exactly the use case for skills. Give precise instructions so it does the task correctly, and save them for later so you can do it again easily.<p>I don't really get how you guys can be so demanding - this technology is magic. It's doing things that 5 years ago we could only dream of. It still blows my mind every time I paste a screenshot of some vague issue along with a quick and dirty prompt and it just gets it and gives me the right answer immediately.<p>In the hands of a competent user these things are absolutely incredible, I can develop solutions faster, with higher quality and less effort. So honestly man all you guys complaining that they aren't good enough? I can't help but think you guys must really not be very competent. Complaining about problems while the solution is staring you in the face.</p>
]]></description><pubDate>Sun, 07 Jun 2026 15:58:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=48436076</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48436076</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48436076</guid></item><item><title><![CDATA[New comment by sfn42 in "Uber's $1,500/month AI limit is a useful signal for AI tool pricing"]]></title><description><![CDATA[
<p>That's why I said "a lot of the time". Not always. And it's not really a problem to de-DRY things, literally just copy/paste and make the change you want. 
The bigger problem in my eyes is when the requirements start to diverge people just add an if branch and soon you have a function/component that does 7 different things depending on how it's used and it's a big buggy mess.<p>It's also possible in many of these cases to identify sub-patterns you could abstract, to create a set of tools you can compose in different ways in order to satisfy the different use cases. Instead of one function/component you make multiple, and use them together.<p>All this stuff is just basic programming but I've mostly given up trying to preach about it. Most people don't care, and even if they did care they just don't have the talent to write really good code. It's rare to find a dev who does really solid work. In my experience you either do it because that's who you are, or nothing I say will make any difference.</p>
]]></description><pubDate>Thu, 04 Jun 2026 17:51:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=48402124</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48402124</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48402124</guid></item><item><title><![CDATA[New comment by sfn42 in "Artificial intelligence is not conscious"]]></title><description><![CDATA[
<p>I don't know why people always need to assign agendas to me in discussions like this. It's not "important to me" it's literally just reality. Consciousness <i>is</i> mysterious, we don't know much about it. The fact that you can mess with it by poking the brain does not mean you understand it.<p>Okay now tell me where in the LLM its alleged consciousness comes from.</p>
]]></description><pubDate>Thu, 04 Jun 2026 15:51:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=48400452</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48400452</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48400452</guid></item><item><title><![CDATA[New comment by sfn42 in "Uber's $1,500/month AI limit is a useful signal for AI tool pricing"]]></title><description><![CDATA[
<p>> Least important thing for a business<p>- Takes weeks or months to get simple features out the door, and when they're out they're buggy as hell and the bugs never get fixed. Sound familiar?<p>> I’d never touch any line of code unless I absolutely have to<p>And this is how legacy code is made. Years of everyone "never touching anything they don't have to" leads to a giant steaming pile of shit.<p>> unless the business is willing to face some down time<p>How does a simple refactor cause downtime? I do this kind of stuff all the time and pretty much never cause any downtime. In the very rare cases that prod downtime does occur it's generally not because of some simple code refactor, and we have it back up in no time by just rolling it back. Unless it's not related to the code at all, in which case it also wasn't a refactor that caused it.</p>
]]></description><pubDate>Thu, 04 Jun 2026 10:19:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=48396541</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48396541</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48396541</guid></item><item><title><![CDATA[New comment by sfn42 in "Artificial intelligence is not conscious – Ted Chiang"]]></title><description><![CDATA[
<p>I agree, exact simulation is nonsensical which is my whole point. Did you read the comment I replied to?<p>It is nonsensical to claim that anything other than my brain could produce the same consciousness that my brain is producing. It's obviously far beyond anything any conceivable digital computer could ever reasonably simulate, and even if you did create a "good" simulation it obviously wouldn't have the same properties that my brain does because it's an entirely different thing than my brain is.</p>
]]></description><pubDate>Thu, 04 Jun 2026 07:49:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=48395506</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48395506</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48395506</guid></item><item><title><![CDATA[New comment by sfn42 in "Artificial intelligence is not conscious – Ted Chiang"]]></title><description><![CDATA[
<p>How can a simulation be human when it isn't human? It's a simulation. A human is a human, a simulation is not. Anything that is not a human, is not a human and can never be a human.<p>And there absolutely is something essential to the concept of being human that we are entirely incapable of replicating artificially. In fact as far as I know we are incapable of synthesizing any kind of life whatsoever. We can't even create the simplest type of living cell imaginable.<p>So to claim that we could just create consciousness, a fundamental property of this "life" thing that we don't properly understand, within a piece of rock is beyond naive. We don't even know what it is or how it is.</p>
]]></description><pubDate>Thu, 04 Jun 2026 07:41:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=48395453</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48395453</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48395453</guid></item><item><title><![CDATA[New comment by sfn42 in "Uber's $1,500/month AI limit is a useful signal for AI tool pricing"]]></title><description><![CDATA[
<p>I have full control of my codebase. I'm not afraid to make changes to it because I know what I'm doing.<p>You would edit Claude.md to say things like what tech the project is using, because that's the entire point of claude.md. It's literally the solution to the exact problem you're complaining about. Any information you want it to know, you put in there and then it knows it. And you can tell Claude to make or update the file for you.<p>I'm not one of the people telling you how smart LLMs are. I'm telling you how to use it efficiently, by not expecting it to know everything but rather provide the information that it needs in order to be a more useful tool.</p>
]]></description><pubDate>Thu, 04 Jun 2026 07:28:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=48395326</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48395326</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48395326</guid></item><item><title><![CDATA[New comment by sfn42 in "Artificial intelligence is not conscious – Ted Chiang"]]></title><description><![CDATA[
<p>Citation needed.<p>Also that's impossible. It is impossible to simulate reality exactly using digital computers. The best we can do is approximate. Doesn't matter how powerful it gets, it'll always just be an approximation.</p>
]]></description><pubDate>Thu, 04 Jun 2026 02:18:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=48392846</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48392846</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48392846</guid></item><item><title><![CDATA[New comment by sfn42 in "Artificial intelligence is not conscious – Ted Chiang"]]></title><description><![CDATA[
<p>Its a computer program. It is literally just a lot of zeroes and ones, sitting there doing nothing.<p>Then a request comes in, and the system does a bunch of calculations using those bits, and spits out a result. The bits are unchanged.<p>When your brain receives input, it is changed. It is constantly active. If it ever stops being active it's dead.<p>So, what exactly is the claim? Are the bits constantly conscious? Do they snap into consciousness when the computer does math with them? Or is it maybe the computer that's conscious while it's processing these bits? How about when it stops doing that and goes back to doing other stuff? Why are these particular bits special? Was the computer always conscious?<p>I feel like the only way anyone could believe LLMs are conscious is if they don't understand how computers work. Of course it isn't conscious, how could it possibly be conscious? Its literally just bits. It's like saying the text in a book is conscious.</p>
]]></description><pubDate>Thu, 04 Jun 2026 02:06:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=48392765</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48392765</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48392765</guid></item><item><title><![CDATA[New comment by sfn42 in "Artificial intelligence is not conscious – Ted Chiang"]]></title><description><![CDATA[
<p>Right? It's a computer program. Of course it isn't conscious.</p>
]]></description><pubDate>Thu, 04 Jun 2026 01:44:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=48392633</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48392633</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48392633</guid></item><item><title><![CDATA[New comment by sfn42 in "Why Custom Attributes in .NET Give Me Nightmares"]]></title><description><![CDATA[
<p>The author is saying the .NET devs did a bad job implementing that, they are not saying you shouldn't use it. So you talking about using attributes is irrelevant to the article, it has nothing to do with developers using attributes nor how they do so.</p>
]]></description><pubDate>Thu, 04 Jun 2026 00:44:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=48392234</link><dc:creator>sfn42</dc:creator><comments>https://news.ycombinator.com/item?id=48392234</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48392234</guid></item></channel></rss>