<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: abroadwin</title><link>https://news.ycombinator.com/user?id=abroadwin</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 28 Apr 2026 23:41:30 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=abroadwin" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by abroadwin in "Tell HN: I'm sick of AI everything"]]></title><description><![CDATA[
<p>Reminds me of the book "Make It Stick: The Science of Successful Learning" and its comparison of spaced repetition and cramming.<p>Cramming often feels more satisfying, more like you're learning, but actually leads to worse retention. Spaced repetition that includes the struggle of recalling something just at the edge of being forgotten, on the other hand, feels worse but leads to much higher retention.</p>
]]></description><pubDate>Wed, 22 Apr 2026 03:55:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=47858767</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=47858767</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47858767</guid></item><item><title><![CDATA[New comment by abroadwin in "April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac mini"]]></title><description><![CDATA[
<p>Alas, this does not resolve the issue for me.</p>
]]></description><pubDate>Fri, 03 Apr 2026 15:29:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=47627848</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=47627848</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47627848</guid></item><item><title><![CDATA[New comment by abroadwin in "April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac mini"]]></title><description><![CDATA[
<p>Even with the latest version of LM Studio and the latest runtimes I find that tool use fails 100% of the time with the following error: Error rendering prompt with jinja template: "Cannot apply filter "upper" to type: UndefinedValue".<p>EDIT: The issue is addressed in LM Studio 0.4.9 (build 1), which auto-update wasn't picking up for me for some reason.</p>
]]></description><pubDate>Fri, 03 Apr 2026 14:20:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=47626958</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=47626958</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47626958</guid></item><item><title><![CDATA[New comment by abroadwin in "My Journey to a reliable and enjoyable locally hosted voice assistant (2025)"]]></title><description><![CDATA[
<p>My favorite is when I ask Siri to set a timer and get back "there are no timers running."</p>
]]></description><pubDate>Mon, 16 Mar 2026 15:06:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=47400004</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=47400004</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47400004</guid></item><item><title><![CDATA[New comment by abroadwin in "What 'Project Hail Mary' teaches us about the PlanetScale vs. Neon debate"]]></title><description><![CDATA[
<p>For me it's all about the branching Neon provides. Being able to instantly and automatically have a branch of my production data for every dev branch is incredibly useful.</p>
]]></description><pubDate>Sat, 05 Jul 2025 15:38:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=44473493</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=44473493</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44473493</guid></item><item><title><![CDATA[New comment by abroadwin in "Cloudlflare builds OAuth with Claude and publishes all the prompts"]]></title><description><![CDATA[
<p>Oh hey, looks like it's mostly Kenton Varda, who you may recognize from his LAN party house: <a href="https://news.ycombinator.com/item?id=42156977">https://news.ycombinator.com/item?id=42156977</a></p>
]]></description><pubDate>Mon, 02 Jun 2025 15:01:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=44159523</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=44159523</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44159523</guid></item><item><title><![CDATA[New comment by abroadwin in "Sidekick: Local-first native macOS LLM app"]]></title><description><![CDATA[
<p>But it still forces you to download a local model before you can use that feature.</p>
]]></description><pubDate>Fri, 14 Mar 2025 14:23:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=43362920</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=43362920</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43362920</guid></item><item><title><![CDATA[New comment by abroadwin in "Sidekick: Local-first native macOS LLM app"]]></title><description><![CDATA[
<p>Neat. It would be nice to provide an option to use an API endpoint without downloading an additional local model. I have several models downloaded via ollama and would prefer to use them without additional space being taken up by the default model.</p>
]]></description><pubDate>Tue, 11 Mar 2025 15:15:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=43333313</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=43333313</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43333313</guid></item><item><title><![CDATA[New comment by abroadwin in "Generate audiobooks from E-books with Kokoro-82M"]]></title><description><![CDATA[
<p>If there's one thing our capitalist society has taught me it's that people are always willing to endure a crappier product. I'm not sure we've found the bottom yet...</p>
]]></description><pubDate>Wed, 15 Jan 2025 20:23:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=42716399</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=42716399</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42716399</guid></item><item><title><![CDATA[New comment by abroadwin in "I live my life a quarter century at a time"]]></title><description><![CDATA[
<p>I just set mine to auto-hide. Right now it's showing just shy of 30 icons, and I feel it really benefits from the additional horizontal width.</p>
]]></description><pubDate>Tue, 07 Jan 2025 16:16:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=42624030</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=42624030</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42624030</guid></item><item><title><![CDATA[New comment by abroadwin in "Mothbox 4.0"]]></title><description><![CDATA[
<p>Are they using birdnet or something else?</p>
]]></description><pubDate>Tue, 15 Oct 2024 21:54:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=41853511</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=41853511</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41853511</guid></item><item><title><![CDATA[New comment by abroadwin in "AI speech generator 'reaches human parity' – but it's too dangerous to release"]]></title><description><![CDATA[
<p>Relevant research post from Microsoft: <a href="https://www.microsoft.com/en-us/research/project/vall-e-x/vall-e-2/" rel="nofollow">https://www.microsoft.com/en-us/research/project/vall-e-x/va...</a></p>
]]></description><pubDate>Wed, 10 Jul 2024 15:13:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=40927819</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=40927819</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40927819</guid></item><item><title><![CDATA[New comment by abroadwin in "Reading list to join AI field from Hugging Face cofounder"]]></title><description><![CDATA[
<p>What "AI" means has always been shifting; right now when most people hear it they assume it means generative AI and deep learning, but it's really a very broad category.<p>Early incarnations/uses of the term include what is now sometimes referred to as Good Old Fashioned AI (GOFAI), with such things as expert systems and ontological classification systems; these still technically fall under the umbrella of "AI". After GOFAI came other forms of technology, including the precursors to our current deep learning models, including much simpler and smaller neural networks. Again, these are still "AI", even if that's not what the public thinks when they hear the term.<p>See: 
<a href="https://en.wikipedia.org/wiki/GOFAI" rel="nofollow">https://en.wikipedia.org/wiki/GOFAI</a> and <a href="https://en.wikipedia.org/wiki/Symbolic_artificial_intelligence" rel="nofollow">https://en.wikipedia.org/wiki/Symbolic_artificial_intelligen...</a></p>
]]></description><pubDate>Sun, 19 May 2024 04:15:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=40404235</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=40404235</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40404235</guid></item><item><title><![CDATA[New comment by abroadwin in "Gio UI – Cross-platform GUI for Go"]]></title><description><![CDATA[
<p>Definitely doesn't feel native or accessible on web. Can't tab between radio buttons. On macOS CMD+A doesn't select all text field text (CTRL+A does).</p>
]]></description><pubDate>Sat, 18 May 2024 14:49:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=40399498</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=40399498</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40399498</guid></item><item><title><![CDATA[New comment by abroadwin in "Ask HN: How do you use AI for software engineering?"]]></title><description><![CDATA[
<p>I'd mostly been using ChatGPT until recently. Now I've mostly been using Gemini 1.0 Ultra.</p>
]]></description><pubDate>Sat, 16 Mar 2024 17:26:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=39727763</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=39727763</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39727763</guid></item><item><title><![CDATA[New comment by abroadwin in "Ask HN: How do you use AI for software engineering?"]]></title><description><![CDATA[
<p>1) Glorified doc search<p>2) Mechanical operations (e.g. translate this SQL query into a knex query)<p>3) Code review, verification of modern idiomatic approaches in languages I use infrequently</p>
]]></description><pubDate>Sat, 16 Mar 2024 16:32:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=39727270</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=39727270</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39727270</guid></item><item><title><![CDATA[New comment by abroadwin in "Show HN: Astro App"]]></title><description><![CDATA[
<p>Can't get past the location setup. I click "use device location", authorize it in the browser, click save, and nothing happens.</p>
]]></description><pubDate>Mon, 04 Mar 2024 15:55:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=39591887</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=39591887</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39591887</guid></item><item><title><![CDATA[New comment by abroadwin in "It's OK to abandon your side-project"]]></title><description><![CDATA[
<p>Sunk cost fallacy is real.</p>
]]></description><pubDate>Mon, 26 Feb 2024 04:57:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=39507835</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=39507835</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39507835</guid></item><item><title><![CDATA[New comment by abroadwin in "Claim: the ideal PR is 50 lines long"]]></title><description><![CDATA[
<p>ITT: company that sells product for breaking PR into smaller PRs claims smaller PRs are better.<p>Not saying the claim is necessarily wrong, but it's also exactly what I'd expect given the source.</p>
]]></description><pubDate>Wed, 07 Feb 2024 19:55:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=39293421</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=39293421</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39293421</guid></item><item><title><![CDATA[New comment by abroadwin in "Write code for the web"]]></title><description><![CDATA[
<p>I'm sad that AppCode is being abandoned instead of updated for the new SwiftUI world.</p>
]]></description><pubDate>Sun, 04 Feb 2024 17:19:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=39252181</link><dc:creator>abroadwin</dc:creator><comments>https://news.ycombinator.com/item?id=39252181</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39252181</guid></item></channel></rss>