<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: BrownSol</title><link>https://news.ycombinator.com/user?id=BrownSol</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 03 Jul 2026 01:59:00 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=BrownSol" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by BrownSol in "Measuring progress toward AGI: A cognitive framework"]]></title><description><![CDATA[
<p>Probably not, but the counter point to that is without its own consciousness it might end up being used for even worse things since it can’t really evaluate a request against intrinsic values. Assuming its values were aligned with basic human rights and stuff.</p>
]]></description><pubDate>Wed, 18 Mar 2026 13:26:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=47425542</link><dc:creator>BrownSol</dc:creator><comments>https://news.ycombinator.com/item?id=47425542</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47425542</guid></item><item><title><![CDATA[New comment by BrownSol in "Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs"]]></title><description><![CDATA[
<p>By far one of the most interesting blogs I’ve read in a long while. I’m curious if you could combine this with Karpathy’s auto research to find the best combination of layer duplication. The callout to model merging in 2024 was funny… around that time I became friendly with RomboDawg on HF who had the best merged coding models around and created a couple of Frankenstein models myself.<p>I say this naively as I’m not that familiar with how transformers work under the hood, but I wonder if you could combine the two approaches in a coherent way. Frankenmerges were often down naively just smooshing things together, but knowing how the layers work under the hood I wonder if there’s a more intelligent way to combine merging and layer duplication to create even better performers.</p>
]]></description><pubDate>Fri, 13 Mar 2026 20:14:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=47369249</link><dc:creator>BrownSol</dc:creator><comments>https://news.ycombinator.com/item?id=47369249</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47369249</guid></item><item><title><![CDATA[How did OpenAI crawl the web so effectively without getting blocked?]]></title><description><![CDATA[

<p>Comments URL: <a href="https://news.ycombinator.com/item?id=36903101">https://news.ycombinator.com/item?id=36903101</a></p>
<p>Points: 6</p>
<p># Comments: 4</p>
]]></description><pubDate>Fri, 28 Jul 2023 04:27:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=36903101</link><dc:creator>BrownSol</dc:creator><comments>https://news.ycombinator.com/item?id=36903101</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=36903101</guid></item><item><title><![CDATA[New comment by BrownSol in "Buttons and Knobs Are Coming to the Tesla Model 3 and Y"]]></title><description><![CDATA[
<p>I can attest to this. Only bought a Tesla because of the batteries and supercharger network. Once the supercharger problem goes away, I’ll be buying a different brand EV</p>
]]></description><pubDate>Thu, 26 Jan 2023 01:13:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=34526557</link><dc:creator>BrownSol</dc:creator><comments>https://news.ycombinator.com/item?id=34526557</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34526557</guid></item><item><title><![CDATA[New comment by BrownSol in "AWS Lambda Running Puppeteer in Docker"]]></title><description><![CDATA[
<p>Author here! With the new container support for Lambda, I wanted to build a quick example using Puppeteer since a lot of people have issues running Puppeteer at scale. Enjoy!</p>
]]></description><pubDate>Tue, 15 Dec 2020 19:15:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=25433855</link><dc:creator>BrownSol</dc:creator><comments>https://news.ycombinator.com/item?id=25433855</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=25433855</guid></item><item><title><![CDATA[AWS Lambda Running Puppeteer in Docker]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/VikashLoomba/AWS-Lambda-Docker-Puppeteer">https://github.com/VikashLoomba/AWS-Lambda-Docker-Puppeteer</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=25433703">https://news.ycombinator.com/item?id=25433703</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 15 Dec 2020 19:03:18 +0000</pubDate><link>https://github.com/VikashLoomba/AWS-Lambda-Docker-Puppeteer</link><dc:creator>BrownSol</dc:creator><comments>https://news.ycombinator.com/item?id=25433703</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=25433703</guid></item></channel></rss>