<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: hambandit</title><link>https://news.ycombinator.com/user?id=hambandit</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 21 Jul 2026 16:04:25 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=hambandit" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Lossless model compression experiment: GLM-5.2 in 25% less memory]]></title><description><![CDATA[
<p>Article URL: <a href="https://brianbell-x.github.io/weight-compression/">https://brianbell-x.github.io/weight-compression/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48979201">https://news.ycombinator.com/item?id=48979201</a></p>
<p>Points: 16</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 20 Jul 2026 14:16:45 +0000</pubDate><link>https://brianbell-x.github.io/weight-compression/</link><dc:creator>hambandit</dc:creator><comments>https://news.ycombinator.com/item?id=48979201</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48979201</guid></item><item><title><![CDATA[New comment by hambandit in "Dataframe 1.0.0.0"]]></title><description><![CDATA[
<p>I learned some haskell as my hobby language a few years back. It was very cool and forced me to think about programming differently (and finally grok recursion). It never felt like a good language for data analysis to me though (maybe that's cause this library wasn't around? lol). This isn't meant a criticism of this library, instead, I'm curious the use cases the author, if you're around or a user, has in mind. Congrats on the v1 release!</p>
]]></description><pubDate>Mon, 23 Mar 2026 13:11:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=47489028</link><dc:creator>hambandit</dc:creator><comments>https://news.ycombinator.com/item?id=47489028</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47489028</guid></item><item><title><![CDATA[Apache DataFusion: Fast, Embeddable, Modular Analytic Query Engine [pdf]]]></title><description><![CDATA[
<p>Article URL: <a href="http://andrew.nerdnetworks.org/other/SIGMOD-2024-lamb.pdf">http://andrew.nerdnetworks.org/other/SIGMOD-2024-lamb.pdf</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=42622449">https://news.ycombinator.com/item?id=42622449</a></p>
<p>Points: 12</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 07 Jan 2025 14:09:54 +0000</pubDate><link>http://andrew.nerdnetworks.org/other/SIGMOD-2024-lamb.pdf</link><dc:creator>hambandit</dc:creator><comments>https://news.ycombinator.com/item?id=42622449</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42622449</guid></item><item><title><![CDATA[New comment by hambandit in "The Internet Is Worse Than a Brainwashing Machine"]]></title><description><![CDATA[
<p><a href="https://web.archive.org/web/20250106142330/https://www.theatlantic.com/technology/archive/2025/01/january-6-justification-machine/681215/" rel="nofollow">https://web.archive.org/web/20250106142330/https://www.theat...</a></p>
]]></description><pubDate>Mon, 06 Jan 2025 20:33:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=42615390</link><dc:creator>hambandit</dc:creator><comments>https://news.ycombinator.com/item?id=42615390</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42615390</guid></item><item><title><![CDATA[New comment by hambandit in "AI makes tech debt more expensive"]]></title><description><![CDATA[
<p>I find this perspective both scary and exciting. I'm curious, how do you validate the LLM's output? If you have a way to do this, and it's working. Then that's amazing. If you don't, how are you gauging "work best"?</p>
]]></description><pubDate>Thu, 14 Nov 2024 22:18:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=42141805</link><dc:creator>hambandit</dc:creator><comments>https://news.ycombinator.com/item?id=42141805</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42141805</guid></item><item><title><![CDATA[New comment by hambandit in "Embeddings are underrated"]]></title><description><![CDATA[
<p>Embeddings from things like one-hot, count vectorization, tf-idf, etc into dimensionality reduction techniques like SVD and PCA have been around for a long time and also provided the ability to compare any two pieces of text to each other. Yes, neural networks and LLMs have provided the ability for the context of each word to affect the whole document's embedding and capture more meaning, potentially that pesky "semantic" sort even; but they still are fundamentally a dimensionality reduction technique.</p>
]]></description><pubDate>Fri, 01 Nov 2024 20:00:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=42020927</link><dc:creator>hambandit</dc:creator><comments>https://news.ycombinator.com/item?id=42020927</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42020927</guid></item><item><title><![CDATA[Consistently faster and smaller compressed bitmaps with Roaring (2016)]]></title><description><![CDATA[
<p>Article URL: <a href="https://arxiv.org/abs/1603.06549">https://arxiv.org/abs/1603.06549</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=42020345">https://news.ycombinator.com/item?id=42020345</a></p>
<p>Points: 54</p>
<p># Comments: 8</p>
]]></description><pubDate>Fri, 01 Nov 2024 18:57:07 +0000</pubDate><link>https://arxiv.org/abs/1603.06549</link><dc:creator>hambandit</dc:creator><comments>https://news.ycombinator.com/item?id=42020345</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42020345</guid></item><item><title><![CDATA[New comment by hambandit in "Notepad++ is 21 years old"]]></title><description><![CDATA[
<p>I remember my college roommate, around 2010, using Notepad++. I assumed it was fairly old at that point given how simple and solid it looked. Way to go, Notepad++ for building something that's standing the test of time!</p>
]]></description><pubDate>Fri, 01 Nov 2024 18:46:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=42020242</link><dc:creator>hambandit</dc:creator><comments>https://news.ycombinator.com/item?id=42020242</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42020242</guid></item></channel></rss>