<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: raylad</title><link>https://news.ycombinator.com/user?id=raylad</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 21 Apr 2026 15:30:14 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=raylad" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by raylad in "Claude Opus 4.7"]]></title><description><![CDATA[
<p>That was more than one task. It was 3.<p>I also had Opus 4.7 and Opus 4.6 do audits of a very long document using identical prompts. I then had Codex 5.4 compare the audits. Codex found that 4.6 did a far better job and 4.7 had missed things and added spurious information.<p>I then asked a new session of Opus 4.7 if it agreed or disagreed with the Codex audit and it agreed with it.<p>I also agreed with it.</p>
]]></description><pubDate>Fri, 17 Apr 2026 04:10:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=47802374</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=47802374</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47802374</guid></item><item><title><![CDATA[New comment by raylad in "Claude Opus 4.7"]]></title><description><![CDATA[
<p>I am using 4.7 with the default extra high thinking, and it is clearly very stupid. It's worse than old Sonnet 4.5.<p>I had it suggest some parameters for BCFtools and it suggested parameters that would do the opposite of what I wanted to do. I pointed out the error and it apologized.<p>It also is not taking any initiative to check things, but wants me to check them (ie: file contents, etc.).<p>And it is claiming that things are "too complex" or "too difficult" when they are super easy. For instance refreshing an AWS token - somehow it couldn't figure out that you could do that in a cron task.<p>A really really bad downgrade. I will be using Codex more now, sadly.</p>
]]></description><pubDate>Fri, 17 Apr 2026 01:22:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=47801557</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=47801557</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47801557</guid></item><item><title><![CDATA[New comment by raylad in "Audio tapes reveal mass rule-breaking in Milgram's obedience experiments"]]></title><description><![CDATA[
<p>One explanation is that the ones who quit believed it was a real experiment and decided they wanted no part of it.<p>The ones who were "obedient" figured out it was fake and treated it as a game.</p>
]]></description><pubDate>Tue, 31 Mar 2026 23:28:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=47594833</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=47594833</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47594833</guid></item><item><title><![CDATA[New comment by raylad in "Multiple Sclerosis"]]></title><description><![CDATA[
<p>N-acetylglucosamine actually is effective against MS.<p>Article: <a href="https://www.ucihealth.org/about-us/news/2023/09/multiple-sclerosis-study" rel="nofollow">https://www.ucihealth.org/about-us/news/2023/09/multiple-scl...</a><p>Paper: "N-acetylglucosamine inhibits inflammation and neurodegeneration markers in multiple sclerosis: a mechanistic trial"<p><a href="https://pubmed.ncbi.nlm.nih.gov/37705084/" rel="nofollow">https://pubmed.ncbi.nlm.nih.gov/37705084/</a><p>It is available fairly inexpensively as a supplement.</p>
]]></description><pubDate>Tue, 31 Mar 2026 23:24:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=47594799</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=47594799</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47594799</guid></item><item><title><![CDATA[New comment by raylad in "Audio tapes reveal mass rule-breaking in Milgram's obedience experiments"]]></title><description><![CDATA[
<p>One question is whether the participants really believed they were giving shocks to the "learners".<p>In college I participated in a number of psychological studies that were similarly deceptive, where one of the other participants was obviously (to me) an actor, or, sometimes, a pre-recorded video.<p>At least one of the studies I participated in was quite like the Milgram study described in the article, where I was supposed to punish another participant. It was very obvious to me that this wasn't really happening, so I randomly punished or didn't punish them, and then afterwards told the researcher that I knew it was all fake.<p>I think many or most other people who saw through the deception probably wouldn't have let the researcher know, because it seemed somehow disrepectful to tell him.<p>No idea if he used my results or, as he should have done, discarded them.</p>
]]></description><pubDate>Tue, 31 Mar 2026 23:11:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=47594702</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=47594702</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47594702</guid></item><item><title><![CDATA[New comment by raylad in "I'm losing the SEO battle for my own open source project"]]></title><description><![CDATA[
<p>So the real site is <a href="https://nanoclaw.dev" rel="nofollow">https://nanoclaw.dev</a><p>(putting this here for the search engines to see)</p>
]]></description><pubDate>Thu, 05 Mar 2026 00:44:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=47256044</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=47256044</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47256044</guid></item><item><title><![CDATA[New comment by raylad in "Fix the iOS keyboard before the timer hits zero or I'm switching back to Android"]]></title><description><![CDATA[
<p>Also why did they get rid of select all? Is there any excuse for that?</p>
]]></description><pubDate>Fri, 13 Feb 2026 16:53:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=47004835</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=47004835</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47004835</guid></item><item><title><![CDATA[New comment by raylad in "Impeccable Style"]]></title><description><![CDATA[
<p>"DON'T use pure white or pure black..."<p>This is something I hate: gray text. Designers love it but it is often very illegible because of inadequate contrast.</p>
]]></description><pubDate>Thu, 15 Jan 2026 21:26:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=46639573</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=46639573</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46639573</guid></item><item><title><![CDATA[New comment by raylad in "Show HN: Mantic.sh – A structural code search engine for AI agents"]]></title><description><![CDATA[
<p>MANTIC_IGNORE_PATTERNS seems not to be implemented, or am I missing something?</p>
]]></description><pubDate>Tue, 06 Jan 2026 20:49:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=46518482</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=46518482</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46518482</guid></item><item><title><![CDATA[New comment by raylad in "Maybe the default settings are too high"]]></title><description><![CDATA[
<p>Or, never play it faster than you can play it perfectly.</p>
]]></description><pubDate>Fri, 26 Dec 2025 01:41:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=46388427</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=46388427</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46388427</guid></item><item><title><![CDATA[New comment by raylad in "Cloth Simulation"]]></title><description><![CDATA[
<p>Feels more like a spiderweb simulation. The fibers are sticky and stretchy.</p>
]]></description><pubDate>Wed, 10 Dec 2025 20:21:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=46223197</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=46223197</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46223197</guid></item><item><title><![CDATA[New comment by raylad in "Bag of words, have mercy on us"]]></title><description><![CDATA[
<p>I tested this with ChatGPT-5.1 and Gemini 3.0. Both correctly (according to Wikipedia at least) stated that George Olshevsky assigned it to its own genus in 1991.<p>This is because there are many words about how to do web searches.</p>
]]></description><pubDate>Mon, 08 Dec 2025 06:42:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=46189156</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=46189156</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46189156</guid></item><item><title><![CDATA[New comment by raylad in "Claude 4.5 Opus' Soul Document"]]></title><description><![CDATA[
<p>It’s a lovely set of aspirations for how a model should behave. But unclear to me is the extent to which expressing those aspirations actually compels the model to follow them.</p>
]]></description><pubDate>Tue, 02 Dec 2025 20:32:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=46126438</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=46126438</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46126438</guid></item><item><title><![CDATA[New comment by raylad in "Where's the shovelware? Why AI coding claims don't add up"]]></title><description><![CDATA[
<p>Some of the projects I've been doing are for myself in other businesses, automating processes that were time consuming or... annoying.<p>Others are for start-ups that are pre-money, pre-revenue where I can build things myself without having to deal with hiring people.<p>In a larger organization, certainly I'd delegate to other people, but if it's just for me or new unfunded start-ups, this is working out very well.<p>And it's not that I "can no longer program". I <i>could</i> program, it's just that I don't find the nuts and bolts of it as interesting as I used to and am more focused on functionality, algorithm, and UI.</p>
]]></description><pubDate>Thu, 04 Sep 2025 06:02:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=45124049</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=45124049</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45124049</guid></item><item><title><![CDATA[New comment by raylad in "Where's the shovelware? Why AI coding claims don't add up"]]></title><description><![CDATA[
<p>I used to be a full-time developer back in the day. Then I was a manager. Then I was a CTO. I stopped doing the day-to-day development and even stopped micro-managing the detailed design.<p>When I tried to code again, I found I didn't really have the patience for it -- having to learn new frameworks, APIs, languages, tricky little details, I used to find it engrossing: it had become annoying.<p>But with tools like Claude Code and my knowledge about how software should be designed and how things should work, I am able to develop big systems again.<p>I'm not 20% more productive than I was. I'm not 10x more productive than I was either. I'm infinity times more productive because I wouldn't be doing it at all otherwise, realistically: I'd either hire someone to do it, or not do it, if it wasn't important enough to go through the trouble to hire someone.<p>Sure, if you are a great developer and spend all day coding and love it, these tools may just be a hindrance. But if you otherwise wouldn't do it at all they are the opposite of that.</p>
]]></description><pubDate>Thu, 04 Sep 2025 02:53:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=45122990</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=45122990</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45122990</guid></item><item><title><![CDATA[New comment by raylad in "Claude Code: Now in Beta in Zed"]]></title><description><![CDATA[
<p>Does this use the API or can it use the Claude subscription?<p>That wasn't stated or perhaps I missed it.</p>
]]></description><pubDate>Thu, 04 Sep 2025 02:41:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=45122909</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=45122909</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45122909</guid></item><item><title><![CDATA[New comment by raylad in "White House in Talks with Intel for 10% U.S. Government Stake"]]></title><description><![CDATA[
<p>We need to be doing much, much more of this so that the country has ownership of substantial percentages of the critical infrastructure, including AI. That seems to be one of the only ways that the citizens in general will be able to share in the fruits of the technology, similarly to how Alaskan citizens get payments from  petroleum.</p>
]]></description><pubDate>Mon, 18 Aug 2025 20:41:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=44945094</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=44945094</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44945094</guid></item><item><title><![CDATA[New comment by raylad in "Claude says “You're absolutely right!” about everything"]]></title><description><![CDATA[
<p>Claude Sonnet 4.0 didn't say "nope" to the same prompt but also didn't agree. It replied:<p>Actually, 24V control signals in HVAC are typically AC, not DC. Most residential and commercial HVAC systems use 24VAC for their control circuits.
This 24VAC comes from a step-down transformer that reduces the standard line voltage (120V or 240V AC) down to 24VAC. The reasons for using AC include:<p>* Safety - Lower voltage reduces shock hazard<p>* Simplicity - Direct transformation from line voltage without need for rectification<p>* Cost - AC transformers are inexpensive and reliable<p>* Compatibility - Most traditional HVAC components (thermostats, contactors, relays, gas valves) are designed for 24VAC<p>However, you will find 24VDC in some applications:<p>* Modern digital/smart thermostats and controls<p>* Building automation systems (BAS)<p>* Some newer high-efficiency equipment<p>* Systems that need to interface with low-voltage DC electronics<p>But if you're working with a typical residential or light commercial HVAC system, assume 24VAC unless specifically noted otherwise. Always verify with a multimeter set to AC voltage when troubleshooting!</p>
]]></description><pubDate>Thu, 14 Aug 2025 00:54:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=44895635</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=44895635</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44895635</guid></item><item><title><![CDATA[New comment by raylad in "Launch HN: Golpo (YC S25) – AI-generated explainer videos"]]></title><description><![CDATA[
<p>Feedback on the text: I find the way that the text generates randomly across the line very distracting because I (and I think most people) read from left to right. Having letters appear randomly is much more difficult to follow.<p>Are there options to have the text appear differently?</p>
]]></description><pubDate>Thu, 14 Aug 2025 00:51:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=44895613</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=44895613</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44895613</guid></item><item><title><![CDATA[New comment by raylad in "Qodo CLI agent scores 71.2% on SWE-bench Verified"]]></title><description><![CDATA[
<p>If it's really better than Claude Code while using Sonnet 4.0, then I'd pay a monthly fee for it, but only if I can use my Claude subscription the same way Claude Code does.<p>I do not want to pay API charges or be limited to a fixed number of "credits" per month.</p>
]]></description><pubDate>Wed, 13 Aug 2025 06:05:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=44885098</link><dc:creator>raylad</dc:creator><comments>https://news.ycombinator.com/item?id=44885098</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44885098</guid></item></channel></rss>