<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: UmYeahNo</title><link>https://news.ycombinator.com/user?id=UmYeahNo</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 13 Jun 2026 08:20:14 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=UmYeahNo" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by UmYeahNo in "Ask HN: Can anyone suggest me a SaaS product idea?"]]></title><description><![CDATA[
<p>SaaS idea generator.</p>
]]></description><pubDate>Wed, 15 Apr 2026 05:09:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=47774905</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=47774905</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47774905</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Ask HN: Anyone Using a Mac Studio for Local AI/LLM?"]]></title><description><![CDATA[
<p>Thanks for the perspective!</p>
]]></description><pubDate>Fri, 06 Feb 2026 05:41:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=46909527</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=46909527</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46909527</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Ask HN: Anyone Using a Mac Studio for Local AI/LLM?"]]></title><description><![CDATA[
<p>Yeah. I'm currently on an Mac Mini m2 Pro with 32GB or ram, and I was so curious how much more I could get out of the Apple ecosystem. Thanks for your perspective.</p>
]]></description><pubDate>Fri, 06 Feb 2026 05:41:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=46909525</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=46909525</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46909525</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Ask HN: Anyone Using a Mac Studio for Local AI/LLM?"]]></title><description><![CDATA[
<p>Thanks for the link. I'll take a look.</p>
]]></description><pubDate>Fri, 06 Feb 2026 05:38:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=46909513</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=46909513</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46909513</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Ask HN: Anyone Using a Mac Studio for Local AI/LLM?"]]></title><description><![CDATA[
<p>Excellent. Thanks for the info!</p>
]]></description><pubDate>Fri, 06 Feb 2026 05:38:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=46909507</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=46909507</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46909507</guid></item><item><title><![CDATA[Ask HN: Anyone Using a Mac Studio for Local AI/LLM?]]></title><description><![CDATA[
<p>Curious to know your experience running local LLM's with a well spec'ed out M3 Ultra or M4 Pro Mac Studio. I don't see a lot of discussion on the Mac Studio for Local LLMs but it seems like you could put big models in memory with the shared VRAM. I assume that the token generation would be slow, but you might get higher quality results because you can put larger models in memory.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46907001">https://news.ycombinator.com/item?id=46907001</a></p>
<p>Points: 57</p>
<p># Comments: 35</p>
]]></description><pubDate>Thu, 05 Feb 2026 23:34:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=46907001</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=46907001</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46907001</guid></item><item><title><![CDATA[New comment by UmYeahNo in "LibriVox"]]></title><description><![CDATA[
<p>Well, you can safely assume that everything in Librivox was used to train the AI. So, "benefit" or "detriment"... you make the call.</p>
]]></description><pubDate>Sun, 01 Jun 2025 22:17:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=44154153</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=44154153</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44154153</guid></item><item><title><![CDATA[New comment by UmYeahNo in "FontDiffuser: Text to Font"]]></title><description><![CDATA[
<p>demo is broken?<p>runtime error
Exit code: ?. Reason: 
Container logs:<p>===== Application Startup at 2024-11-04 13:47:44 =====</p>
]]></description><pubDate>Wed, 23 Apr 2025 21:09:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=43776639</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=43776639</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43776639</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Are You a Good Estimator?"]]></title><description><![CDATA[
<p>Very helpful that it doesn't tell you which ones you got wrong. /s</p>
]]></description><pubDate>Thu, 17 Apr 2025 14:06:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=43717076</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=43717076</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43717076</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Ask HN: Why is OpenAI pivoting to social networks?"]]></title><description><![CDATA[
<p>Perhaps a local idiom to my area, not sure.  It means getting into someones "business", in the same sense as "mind your own business". If you're getting up into my chicken, then you're sticking your nose into my business.</p>
]]></description><pubDate>Tue, 15 Apr 2025 19:14:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=43697199</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=43697199</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43697199</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Ask HN: Why is OpenAI pivoting to social networks?"]]></title><description><![CDATA[
<p>Hypothesis: Elon created Grok to get up in Altman's chicken, so turnabout is fair-play.</p>
]]></description><pubDate>Tue, 15 Apr 2025 17:07:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=43695649</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=43695649</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43695649</guid></item><item><title><![CDATA[New comment by UmYeahNo in "The McMurtry Spéirling is the first car in the world to DRIVE UPSIDE DOWN"]]></title><description><![CDATA[
<p>The fact that it only drove a few inches, at virtually standstill speed is somehow more impressive. From the title I expected some 100mph momentarily upside down barrel roll type scenario.</p>
]]></description><pubDate>Fri, 11 Apr 2025 21:24:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=43658774</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=43658774</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43658774</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Ask HN: Can we please come up with a better name than "Vibe Coding"?"]]></title><description><![CDATA[
<p>Vibe Copy-and-Pasting?</p>
]]></description><pubDate>Wed, 02 Apr 2025 20:36:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=43561214</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=43561214</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43561214</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Whatword.wtf: Calm, non-competitive, web-based, multiplayer word-guessing game"]]></title><description><![CDATA[
<p><i>kinda fun</i>, but with issues. 
In a timed game, what kind of error is "That was a bit to quick". How quick is "too quick".<p>Also, total bummer that if you make the same guess twice it counts as two guesses, rather than saying "Already guessed".</p>
]]></description><pubDate>Wed, 02 Apr 2025 20:32:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=43561169</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=43561169</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43561169</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Let me AI that for you"]]></title><description><![CDATA[
<p>Um. Yeah... No.</p>
]]></description><pubDate>Tue, 04 Feb 2025 05:02:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=42928218</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=42928218</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42928218</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Show HN: Meelo, self-hosted music server for collectors and music maniacs"]]></title><description><![CDATA[
<p>Thank you!</p>
]]></description><pubDate>Thu, 30 Jan 2025 02:09:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=42873963</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=42873963</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42873963</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Show HN: Meelo, self-hosted music server for collectors and music maniacs"]]></title><description><![CDATA[
<p>What are you using to manage artist and album artist tags for your jellyfin server? I've been trying with Picard and both artist and album artist are a mess for me in jellyfin. I'm probably doing something wrong.</p>
]]></description><pubDate>Wed, 29 Jan 2025 02:01:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=42860635</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=42860635</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42860635</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Scheduled tasks in ChatGPT"]]></title><description><![CDATA[
<p>I tried this yesterday, asking it to create a simple daily reminder task, which it happily did. Then when the time came and went I simply got a chat that the task failed, with no explanation of <i>why</i> or <i>how</i> it failed. When I asked it why, it hallucinated that I had too many tasks. (I only had the one) So, now I don't know why it failed or how to fix it.  Which leads to two related observations:<p>1) I find it interesting that the LLM rarely seems trained to understand it's own features, or about your account, or how the LLM works. Seems strange that it has no idea about it's own support.<p>2) Which leads me to the Open AI support docs[0]. It seems pretty telling to me that they use old-school search and not an LLM for its own help docs, right?<p>[0] <a href="https://help.openai.com/" rel="nofollow">https://help.openai.com/</a></p>
]]></description><pubDate>Wed, 15 Jan 2025 20:50:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=42716744</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=42716744</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42716744</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Ask HN: Why Are You Here?"]]></title><description><![CDATA[
<p>Mostly to hear the penetrating opinions of seaofliberty.</p>
]]></description><pubDate>Wed, 08 Jan 2025 05:35:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=42631282</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=42631282</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42631282</guid></item><item><title><![CDATA[New comment by UmYeahNo in "Building a Knowledge System That Enhances Rather Than Replaces Thought"]]></title><description><![CDATA[
<p>What you're describing sounds an awful lot like a barebones obsidian vault.(<a href="https://obsdian.md" rel="nofollow">https://obsdian.md</a>)<p>I'm not familiar with the OP's notion of a "zettlegarden" but I get the impression that they want something a bit more than just markdown files. Perhaps the idea is to increase the notion of connection between captured notes, whether intentional created, or "serendipitous".</p>
]]></description><pubDate>Fri, 03 Jan 2025 02:23:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=42581571</link><dc:creator>UmYeahNo</dc:creator><comments>https://news.ycombinator.com/item?id=42581571</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42581571</guid></item></channel></rss>