<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: ulrikrasmussen</title><link>https://news.ycombinator.com/user?id=ulrikrasmussen</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 17 Aug 2026 08:09:40 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=ulrikrasmussen" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by ulrikrasmussen in "Abdominal fat predicts heart disease risk better than BMI"]]></title><description><![CDATA[
<p>The vast majority of people who lose weight by calorie restriction gain it back, so I wouldn't call it highly effective. Short term yes, but long term, definitely not.</p>
]]></description><pubDate>Sun, 16 Aug 2026 04:25:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=49316896</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49316896</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49316896</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Stop sending me huge PRs; a rant"]]></title><description><![CDATA[
<p>If you generate PRs too big to review for others, then they are too big to review for yourself. This means you are delegating the task of understanding the code to an LLM, and the end result is inevitably that noone in the organization understands the code better than someone who just walked in the door. They can write the next LLM prompt just as well as you because they know as little about the system as you.<p>In that situation I ask you: what is your moat as a software company? Why would your customers keep paying you when companies like Anthropic can just do your-software-company-as-a-service and cut out the middle man and six figure salaries?</p>
]]></description><pubDate>Sat, 15 Aug 2026 05:07:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=49307817</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49307817</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49307817</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Stop sending me huge PRs; a rant"]]></title><description><![CDATA[
<p>I have had some success with asking the LLM to rewrite the commit history after the feature was written. I often have a good idea of a good conceptual split, and the LLM has no problem doing the soul-crushing work of manually pulling out individual files or hunks into a sequence of commits and making sure each builds.<p>I <i>need</i> to do this before I can even review the code myself, and I review everything before I send it to my colleagues for their review.</p>
]]></description><pubDate>Sat, 15 Aug 2026 04:51:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=49307743</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49307743</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49307743</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Choosing an AI model: one prompt, 11 models, different results"]]></title><description><![CDATA[
<p>I think both can be interesting, but surely the 100 words will lead to a lot of variability in the exact shape of the result because so much of the spec will be left up to the LLM. However, it is still interesting to judge the <i>quality</i> of the result and how self-consistent it is. Not by looking at the actual webpage, but by looking at the code and whether it is nicely organized, makes proper use of abstractions, and in general doesn't feel like spaghetti.</p>
]]></description><pubDate>Fri, 14 Aug 2026 06:02:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=49295200</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49295200</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49295200</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Mushroom behind 'tiny people' hallucinations identified"]]></title><description><![CDATA[
<p>Maybe not, I don't know. But at least we understand the pharmacology of many of them, which I guess is what I actually meant.</p>
]]></description><pubDate>Thu, 13 Aug 2026 10:02:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=49283744</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49283744</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49283744</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Mushroom behind 'tiny people' hallucinations identified"]]></title><description><![CDATA[
<p>I think this is so fascinating because the hallucinations sound unlike anything else produced by psychedelics and other psychoactive substances, so I really look forward to learning what the mechanism is.<p>From the stories I've read it also doesn't sound people are experiencing outright delirium although the experience can probably be pretty stressful if you don't know what is happening.</p>
]]></description><pubDate>Thu, 13 Aug 2026 07:53:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=49282927</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49282927</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49282927</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "The Psychedelic Toad of the Sonoran Desert"]]></title><description><![CDATA[
<p>Most recent I know of: <a href="https://www.psychiatrictimes.com/view/blp-003-for-treatment-resistant-depression-phase-2b-patient-enrollment-completed" rel="nofollow">https://www.psychiatrictimes.com/view/blp-003-for-treatment-...</a><p>Mebufotenin is 5-MeO-DMT</p>
]]></description><pubDate>Mon, 10 Aug 2026 19:11:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=49248283</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49248283</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49248283</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "I made tinnitus my friend, then it disappeared [video]"]]></title><description><![CDATA[
<p>My doctor told me the same, but I think it's the wrong way to phrase it because I truly expected them to become invisible and got frustrated when they didn't. What they mean when they say that is probably that you learn to ignore them (unless you can't stop focusing on them), but they are by no means erased.</p>
]]></description><pubDate>Mon, 10 Aug 2026 11:35:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=49242304</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49242304</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49242304</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "I made tinnitus my friend, then it disappeared [video]"]]></title><description><![CDATA[
<p>I got a large amount of floaters in my left eye after a sparring session where I was hit in the eye. Also had flashing in the periphery of my vision when I moved my eye, so I went to an eye doctor to have it examined. Luckily he couldn't see any signs of detachment and it's also been stable for well over a decade and a half now without any worsening.<p>I find that they mostly don't annoy me now, but it genuinely took almost ten years for me to get to that stage. I would focus on them all the time, in particular during a period where I suffered from severe health anxiety.<p>In general I feel much less anxious about everything now than I have previously, and incidentally now is also when I almost don't notice either the floaters or my (very) mild tinnitus.</p>
]]></description><pubDate>Mon, 10 Aug 2026 09:39:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=49241444</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49241444</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49241444</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Message your other Claude Code sessions"]]></title><description><![CDATA[
<p>I have a shell script that sends a message to me on Slack, and I have instructions in CLAUDE.md that it should be invoked when a long task finishes or if my attention is needed. The Slack app API key is one way messaging, so it doesn't allow Claude to exfiltrate anything.</p>
]]></description><pubDate>Sun, 09 Aug 2026 18:59:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=49234509</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49234509</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49234509</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Taste Is All That's Left"]]></title><description><![CDATA[
<p>I also don't think it will kill creativity in the space, although my phrasing might have suggested that, just that it might diminish it and make implementation styles more conformative.<p>On the other hand, we might trade that for creativity in other more high level designs where things like coding style is an unimportant detail for the experiment. For example, I have started playing around with microcontrollers because I can have the LLM generate the software while I focus on learning how to solder and think about how to modularize my hobby automation system. That's creativity and taste at a higher level which I didn't have access to before because I didn't want to invest my precious free time in learning the software ecosystem.</p>
]]></description><pubDate>Fri, 07 Aug 2026 05:21:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=49206150</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49206150</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49206150</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Taste Is All That's Left"]]></title><description><![CDATA[
<p>An important feature of taste is also that it is highly variable between people, and because there is no system or proof of good taste, we cannot really say that one person's taste is objectively better than another's. This is what causes one person to build a large software system in a classical OOP language while another builds almost the same system in a typed functional language, each following their own internal logic of what is good taste. In the end we learn something from it, and maybe someone who worked on both projects refine their taste and starts preferring something that lies in between the two paradigms and comes up with a new interesting programming language.<p>One thing I fear is going to happen when more and more people use LLM's for coding is that they will default to the "average taste" of the LLM, and we will stop getting new interesting ideas about how to build things.</p>
]]></description><pubDate>Fri, 07 Aug 2026 03:28:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=49205610</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49205610</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49205610</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Could psilocybin be the key to treating anorexia?"]]></title><description><![CDATA[
<p>I lost a family member to anorexia, and the only thing I really regret is that I didn't suggest that we try psychedelic therapy now that everything else had failed and things looked pretty grim. I mostly blame myself for not pushing the idea. But I am also angry at the war on drugs which has caused all use of psychoactive drugs to be associated with such taboo.</p>
]]></description><pubDate>Wed, 05 Aug 2026 13:29:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=49182625</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49182625</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49182625</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "A big win for Android interoperability"]]></title><description><![CDATA[
<p>There's Curve Pay which works on GrapheneOS</p>
]]></description><pubDate>Sun, 02 Aug 2026 10:40:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=49143151</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49143151</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49143151</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Dubious research tied to Red Bull has shaped energy drink policy"]]></title><description><![CDATA[
<p>I ended up brewing just one cup of filter in the morning, then drinking one more cup when I arrive at the office. I have a rule to stop before 9am which I found is the latest I can do caffeine without disrupting my sleep. I think I am one of the slow metabolizers.</p>
]]></description><pubDate>Sat, 01 Aug 2026 08:08:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=49132223</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49132223</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49132223</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Dubious research tied to Red Bull has shaped energy drink policy"]]></title><description><![CDATA[
<p>I quit cold turkey and consumed around 1200mg/day, not by drinking energy drinks but coffee, 6 strong cups of filter or more. I made sure to also quit caffeinated sort drinks and switched to herbal tea.<p>The immediate withdrawal symptoms started after around 24h and consisted of headache, cold sweats and brain fog that lasted around three days and seriously impeded my ability to work. However, the psychological craving just... never really got better once it plateaued. I always felt a bit more understimulated than before I stopped, and a bit less motivated.<p>I kept it up for about 1.5 years or so before I decided it wasn't worth it. The first cup of coffee seriously gave me euphoria comparable to a low dose of amphetamine. That was so pleasurable that I tried to keep my consumption to one cup per week, but even with that spacing I felt the tolerance build up again.</p>
]]></description><pubDate>Sat, 01 Aug 2026 07:47:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=49132108</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49132108</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49132108</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "The session you cannot take with you"]]></title><description><![CDATA[
<p>A password manager has an almost as efficient UX</p>
]]></description><pubDate>Fri, 31 Jul 2026 13:56:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=49123196</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49123196</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49123196</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Agent Skill to Force Docs in ASD-STE100 Simplified Technical English"]]></title><description><![CDATA[
<p>I don't know if I have been damaged by reading so much AI, but I swear the narrator of that video had the script for it written by Claude without any of those rules applied. There are so many platitudes and AI-isms in the way he speaks:<p><pre><code>    "now the honesty - those translation gains were real but small"
    "and here is the honest part"
    "same disease but with different symptom"
    "so that brutal 3% number was a Claude quirk, not a law of nature"</code></pre></p>
]]></description><pubDate>Fri, 31 Jul 2026 08:40:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=49120554</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49120554</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49120554</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Agent Skill to Force Docs in ASD-STE100 Simplified Technical English"]]></title><description><![CDATA[
<p>And the goddamn emojis. I get it, people use them when texting to make the writing a bit more chummy, but I can really live without them everywhere else.</p>
]]></description><pubDate>Fri, 31 Jul 2026 07:19:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=49120025</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49120025</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49120025</guid></item><item><title><![CDATA[New comment by ulrikrasmussen in "Truth is not a direction: a Tarski attack on LLM probes"]]></title><description><![CDATA[
<p>Diagnosis of rare diseases is a subset of "true" statements, no?</p>
]]></description><pubDate>Wed, 29 Jul 2026 07:37:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=49094473</link><dc:creator>ulrikrasmussen</dc:creator><comments>https://news.ycombinator.com/item?id=49094473</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49094473</guid></item></channel></rss>