<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: hatefulmoron</title><link>https://news.ycombinator.com/user?id=hatefulmoron</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 19 Jun 2026 22:02:40 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=hatefulmoron" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by hatefulmoron in "UK Brings in Full Social Media Ban for Under-16s"]]></title><description><![CDATA[
<p>I mean, we view social networks as having network effects that keep people there. The same force that stops people from switching from Facebook and TikTok prevents people from abandoning social media altogether. Waiting for all the adults to be responsible and forward thinking seems a little far fetched.</p>
]]></description><pubDate>Mon, 15 Jun 2026 09:33:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=48538829</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=48538829</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48538829</guid></item><item><title><![CDATA[New comment by hatefulmoron in "UK Brings in Full Social Media Ban for Under-16s"]]></title><description><![CDATA[
<p>I'm not in favor of these social media bans, but I would think the benefit here is that without the ban your child will be in the "real world" while everybody else's is on social media. This would make the "real world" socialization benefits more difficult.</p>
]]></description><pubDate>Mon, 15 Jun 2026 09:22:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=48538733</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=48538733</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48538733</guid></item><item><title><![CDATA[New comment by hatefulmoron in "I Am Retiring from Tech to Live Offline"]]></title><description><![CDATA[
<p>Aren't they related in the sense that they're not tech/SaaS/software related? "I'm looking into being an elevator mechanic; I need the money because my wife is pregnant." and then "I'm writing poetry by hand." Like, their life is going in a non-tech direction?</p>
]]></description><pubDate>Fri, 29 May 2026 15:38:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=48324593</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=48324593</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48324593</guid></item><item><title><![CDATA[New comment by hatefulmoron in "College students drown out AI-praising commencement speeches with boos"]]></title><description><![CDATA[
<p>Who do you imagine the winners and losers will be? To the extent AI is useful and disruptive, it's best utilized by people with capital. Which is to say, the winners are few and the losers are everybody else. In this case, the losers aren't just more vocal, they're louder and more visible because they're much more numerous.</p>
]]></description><pubDate>Wed, 20 May 2026 16:07:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=48209992</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=48209992</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48209992</guid></item><item><title><![CDATA[New comment by hatefulmoron in "I'm going back to writing code by hand"]]></title><description><![CDATA[
<p>How am I being virulently anti-AI? I've been a Claude Code max subscriber for many months and find it very helpful. It feels a little unfair to conclude that any criticism is just unfounded fear and insecurity..</p>
]]></description><pubDate>Tue, 12 May 2026 01:11:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=48102950</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=48102950</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48102950</guid></item><item><title><![CDATA[New comment by hatefulmoron in "I'm going back to writing code by hand"]]></title><description><![CDATA[
<p>I could also include the correct implementation for it to copy in the prompt, if you get what I'm trying to say. Some amount of laziness or vagueness in the prompt is an intended use case, it's surely the point of having the subagents do so much churning of tokens to research before writing the plan that I'm about to disregard. But sure, those are helpful tips.</p>
]]></description><pubDate>Mon, 11 May 2026 17:09:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=48097694</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=48097694</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48097694</guid></item><item><title><![CDATA[New comment by hatefulmoron in "I'm going back to writing code by hand"]]></title><description><![CDATA[
<p>You're right. I think having it spawn lots of subagents, read everything, formulate a big and detailed plan, only for it to be subtly wrong while requiring me to carefully review the result and the intermediate plans that produced it is quite tiring. I suppose things slip through.</p>
]]></description><pubDate>Mon, 11 May 2026 15:39:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=48096468</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=48096468</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48096468</guid></item><item><title><![CDATA[New comment by hatefulmoron in "I'm going back to writing code by hand"]]></title><description><![CDATA[
<p>Plan mode improves results, but it doesn't solve the underlying problems. Pretty often Claude Opus 4.7 on xhigh will formulate a reasonable enough plan, churn for a while, then come back with a summary that it didn't stick to the plan because it wasn't accurate.<p>Worse, the disclaimer is buried under a bunch of "did X, did Y on line Z of file a/b/c", as if it's just a minor inconvenience. To the extent the plan was inaccurate, you're left in an undefined state where you might as well undo what it just did..</p>
]]></description><pubDate>Mon, 11 May 2026 15:15:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=48096150</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=48096150</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48096150</guid></item><item><title><![CDATA[New comment by hatefulmoron in "IQuest-Coder: A new open-source code model beats Claude Sonnet 4.5 and GPT 5.1 [pdf]"]]></title><description><![CDATA[
<p>I wouldn't use any provider: z.ai, Claude, OpenAI, ... if I was concerned about the government obtaining my prompts. If you're doing something where this is a legitimate concern (as opposed to my open source stuff), you should get a local LLM or put a lot of effort into anonymizing yourself and your prompts.</p>
]]></description><pubDate>Sun, 04 Jan 2026 20:55:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=46492090</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=46492090</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46492090</guid></item><item><title><![CDATA[New comment by hatefulmoron in "IQuest-Coder: A new open-source code model beats Claude Sonnet 4.5 and GPT 5.1 [pdf]"]]></title><description><![CDATA[
<p>Yeah, when I say "current day Claude" I'm referring to Opus 4.5, which is what I always use on the max plan.</p>
]]></description><pubDate>Sun, 04 Jan 2026 20:53:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=46492070</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=46492070</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46492070</guid></item><item><title><![CDATA[New comment by hatefulmoron in "IQuest-Coder: A new open-source code model beats Claude Sonnet 4.5 and GPT 5.1 [pdf]"]]></title><description><![CDATA[
<p>I got their z.ai plan to test alongside my Claude subscription; it feels about on par with something between sonnet 4.0 and sonnet 4.5. It's definitely a few steps below current day Claude, but it's very capable.</p>
]]></description><pubDate>Sat, 03 Jan 2026 10:29:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=46475004</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=46475004</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46475004</guid></item><item><title><![CDATA[New comment by hatefulmoron in "GPT-5.2-Codex"]]></title><description><![CDATA[
<p>I've had the $20/month plan for a few months alongside a max subscription to Claude; the cheap codex plan goes a really long way. I use it a few times a day for debugging, finding bugs, and reviewing my work. I've ran out of usage a couple of times, but only when I lean on it way more than I should.<p>I only ever use it on the high reasoning mode, for what it's worth. I'm sure it's even less of a problem if you turn it down.</p>
]]></description><pubDate>Fri, 19 Dec 2025 01:10:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=46321116</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=46321116</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46321116</guid></item><item><title><![CDATA[New comment by hatefulmoron in "Dafny: Verification-Aware Programming Language"]]></title><description><![CDATA[
<p>Dafny and similar languages use SMT; their semantics need to be such that you're giving enough information for your proof to verify in sufficient time, otherwise you'll be waiting for a very long time or your proof is basically undecidable.<p>I'm not sure about benchmarks comparing languages, but Dafny goes through a lot of tweaking to make the process faster.</p>
]]></description><pubDate>Wed, 17 Dec 2025 04:25:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=46298240</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=46298240</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46298240</guid></item><item><title><![CDATA[New comment by hatefulmoron in "Do the thinking models think?"]]></title><description><![CDATA[
<p>Is that interesting? Computers accomplish all sorts of tasks which require thinking from humans.. without thinking. Chess engines have been much better than me at chess for a long time, but I can't say there's much thinking involved.</p>
]]></description><pubDate>Mon, 01 Dec 2025 08:20:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=46104835</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=46104835</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46104835</guid></item><item><title><![CDATA[New comment by hatefulmoron in "After my dad died, we found the love letters"]]></title><description><![CDATA[
<p>I admit that when reading the description of your relationship (I don't mean to be disrespectful, for what it's worth) I can't help but wonder how it can possibly be consistent with "a relationship between two people can be basically whatever they want it to be." It really reads like the relationship is whatever _she_ wants it to be.<p>If you had come into the relationship with the understanding that you'd both date/have sex with other people then great; it doesn't matter what other people think. However, when you say that it was hard for you to accept her being with other men, and that you're lucky that "she has never fallen in love and wanted to run away with one of em", damn. My first instinct is that you should take your own advice: find or design a relationship where you don't have to accept this.<p>I realize that some of my knee jerk reaction might just be instinct/cultural values, I mean no disrespect.</p>
]]></description><pubDate>Sun, 23 Nov 2025 15:09:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=46024111</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=46024111</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46024111</guid></item><item><title><![CDATA[New comment by hatefulmoron in "Open-source Zig book"]]></title><description><![CDATA[
<p>If you believed that you wouldn't explicitly say there was no AI generated content at all, you'd let it speak for itself.</p>
]]></description><pubDate>Mon, 17 Nov 2025 00:12:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=45949740</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=45949740</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45949740</guid></item><item><title><![CDATA[New comment by hatefulmoron in "Ask HN: How to deal with long vibe-coded PRs?"]]></title><description><![CDATA[
<p>You're proposing a truism: if you don't get a good result, it's either because your query is bad or because the LLM isn't good enough to provide a good result.<p>Yes, that is how this works. I'm talking about the case where you're providing a good query and getting poor results. Claiming that this can be solved by more LLM conversations and ultrathink is cope.</p>
]]></description><pubDate>Tue, 04 Nov 2025 10:03:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=45809222</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=45809222</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45809222</guid></item><item><title><![CDATA[New comment by hatefulmoron in "Ask HN: How to deal with long vibe-coded PRs?"]]></title><description><![CDATA[
<p>I've read your questions a few times and I'm a bit perplexed. What kind of answers are you expecting me to give you here? Surely if you use Claude Code or other tools you'd know that the answers are so varying and situation specific it's not really possible for me to give you solid answers.</p>
]]></description><pubDate>Tue, 04 Nov 2025 09:19:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=45808957</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=45808957</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45808957</guid></item><item><title><![CDATA[New comment by hatefulmoron in "Ask HN: How to deal with long vibe-coded PRs?"]]></title><description><![CDATA[
<p>Distinction without a difference. I'm talking about its output being insufficient, whatever word you want to use for output.</p>
]]></description><pubDate>Tue, 04 Nov 2025 09:02:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=45808857</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=45808857</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45808857</guid></item><item><title><![CDATA[New comment by hatefulmoron in "Ask HN: How to deal with long vibe-coded PRs?"]]></title><description><![CDATA[
<p>I have a Claude max subscription. When I think of bad Claude code, I'm not thinking about unused variable definitions. I'm thinking about the times you turn on ultrathink, allow it to access tools and negotiate it's solution, and it still churns out an over complicated yet partially correct solution that breaks.   I totally trust Claude to fix linting errors.</p>
]]></description><pubDate>Tue, 04 Nov 2025 08:29:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=45808704</link><dc:creator>hatefulmoron</dc:creator><comments>https://news.ycombinator.com/item?id=45808704</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45808704</guid></item></channel></rss>