<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: elpalek</title><link>https://news.ycombinator.com/user?id=elpalek</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 16 Apr 2026 04:04:33 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=elpalek" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Show HN: I ported DOOM to GitHub Universe 2025 conference badge]]></title><description><![CDATA[
<p>Fully playable on RP2350 with 6 buttons. Fire and select shares the same key.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47400451">https://news.ycombinator.com/item?id=47400451</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 16 Mar 2026 15:38:49 +0000</pubDate><link>https://github.com/yudataguy/badge-doom</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=47400451</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47400451</guid></item><item><title><![CDATA[New comment by elpalek in "Claude Code On-the-Go"]]></title><description><![CDATA[
<p>I don't like claude code web due to its lack of planning mode. I found the result is often lackluster compare to claude code cli.<p>My current setup: Tailscale + Terminus(ipad) + home machine(code base)<p>Need to look into how to work on multiple features at the same time next.</p>
]]></description><pubDate>Sun, 04 Jan 2026 21:09:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=46492255</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=46492255</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46492255</guid></item><item><title><![CDATA[New comment by elpalek in "Proton Mail suspended journalist accounts at request of cybersecurity agency"]]></title><description><![CDATA[
<p>I wouldn't trust Zoho. More than 10 years ago, they shadowbanned (can not be shared or publicly viewed) my documents because it criticized Chinese communist party.</p>
]]></description><pubDate>Sat, 13 Sep 2025 04:21:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=45229268</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=45229268</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45229268</guid></item><item><title><![CDATA[New comment by elpalek in "Ask HN: What are you working on? (July 2025)"]]></title><description><![CDATA[
<p>I'm building a information hub that utilize AI agents to compile all the relevant information from China (gov, econ, commerce, anything and everything). I call it "information domination". Heard many times that language barrier stops people having a better understanding of China. Now the LLM translation is good enough, and AI agents can do way more in information gathering stage. It's time to put things in practice.<p><a href="https://wallnot.com" rel="nofollow">https://wallnot.com</a><p>For now, it only has a daily newsletter fully compiled by AI agents without any human intervention. I plan to add public listed companies (semiconductor, energy provider, etc) onto the platform. Already found lots of good data points that can be used by analysts, researchers or observers.</p>
]]></description><pubDate>Sun, 27 Jul 2025 19:52:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=44704122</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=44704122</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44704122</guid></item><item><title><![CDATA[New comment by elpalek in "DaisyUI: Tailwind CSS Components"]]></title><description><![CDATA[
<p>Q: Has anyone used claude working with DaisyUI? Don't like claude's default ui choices.</p>
]]></description><pubDate>Tue, 22 Jul 2025 18:04:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=44650868</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=44650868</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44650868</guid></item><item><title><![CDATA[New comment by elpalek in "Ask HN: What Are You Working On? (June 2025)"]]></title><description><![CDATA[
<p>AI Anime Recommendation Engine<p><a href="https://oshianime.com" rel="nofollow">https://oshianime.com</a></p>
]]></description><pubDate>Mon, 30 Jun 2025 00:46:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=44418043</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=44418043</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44418043</guid></item><item><title><![CDATA[New comment by elpalek in "Launch HN: Chonkie (YC X25) – Open-Source Library for Advanced Chunking"]]></title><description><![CDATA[
<p>Do you have a benchmark for comparing different chunking methods?
Your existing benchmark is to compare different libraries.</p>
]]></description><pubDate>Tue, 10 Jun 2025 00:10:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=44231089</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=44231089</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44231089</guid></item><item><title><![CDATA[New comment by elpalek in "Show HN: HelixDB – Open-source vector-graph database for AI applications (Rust)"]]></title><description><![CDATA[
<p>my project deals w/ non-english text, bm25 performance is middeling. Language specific sparse model helps.</p>
]]></description><pubDate>Tue, 13 May 2025 22:35:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=43978518</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=43978518</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43978518</guid></item><item><title><![CDATA[New comment by elpalek in "Show HN: Helixdb – Open-source vector-graph database for AI applications (Rust)"]]></title><description><![CDATA[
<p>have you thought about SPALDE models? ex: <a href="https://arxiv.org/abs/2109.10086" rel="nofollow">https://arxiv.org/abs/2109.10086</a></p>
]]></description><pubDate>Tue, 13 May 2025 20:21:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=43977253</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=43977253</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43977253</guid></item><item><title><![CDATA[New comment by elpalek in "PDF to Text, a challenging problem"]]></title><description><![CDATA[
<p>Recently tested a (non-english) pdf ocr with Gemini 2.5 Pro. 
First, directly ask it to extract text from pdf. Result: random text blob, not useable.<p>Second, I converted pdf into pages of jpg. Gemini performed exceptional. Near perfect text extraction with intact format in markdown.<p>Maybe there's internal difference when processing pdf vs jpg inside the model.</p>
]]></description><pubDate>Tue, 13 May 2025 20:00:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=43977047</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=43977047</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43977047</guid></item><item><title><![CDATA[New comment by elpalek in "Show HN: Helixdb – Open-source vector-graph database for AI applications (Rust)"]]></title><description><![CDATA[
<p>What method/model are you using for sparse search?</p>
]]></description><pubDate>Tue, 13 May 2025 19:55:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=43976983</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=43976983</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43976983</guid></item><item><title><![CDATA[New comment by elpalek in "Ask HN: What are you working on? (March 2025)"]]></title><description><![CDATA[
<p>Will let you know once android version is public</p>
]]></description><pubDate>Mon, 31 Mar 2025 18:03:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=43537867</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=43537867</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43537867</guid></item><item><title><![CDATA[New comment by elpalek in "Ask HN: What are you working on? (March 2025)"]]></title><description><![CDATA[
<p>Japan Top 100 (restaurants) app<p><a href="https://apps.apple.com/us/app/japan-top-100/id6741251616">https://apps.apple.com/us/app/japan-top-100/id6741251616</a><p>Only public on iOS store for now, due to Google requires larger # of testers to authenticate the app.<p>This app idea came from my last Japan trip. I had a hard time finding good local restaurants (not tourist traps). So I decided to build this app with Japanese-oriented lists, due to lists' lacked of maps, etc. The app actually helped me discover some great spots, since it lists places all over Japan. Please give it a try and let me know if you have any feature requests or ideas.</p>
]]></description><pubDate>Sun, 30 Mar 2025 22:54:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=43528581</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=43528581</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43528581</guid></item><item><title><![CDATA[New comment by elpalek in "How I got 100% off my train travel"]]></title><description><![CDATA[
<p>China's land area is approximately 25 times of Japan, def has a bigger network. But the top speed is comparable in current generations[1] except the Maglev.<p>1. <a href="https://www.railway-technology.com/features/the-10-fastest-high-speed-trains-in-the-world/?cf-view" rel="nofollow">https://www.railway-technology.com/features/the-10-fastest-h...</a></p>
]]></description><pubDate>Thu, 20 Mar 2025 05:30:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=43420118</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=43420118</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43420118</guid></item><item><title><![CDATA[New comment by elpalek in "How I got 100% off my train travel"]]></title><description><![CDATA[
<p>Can you please elaborate on the Chinese advantage?</p>
]]></description><pubDate>Thu, 20 Mar 2025 01:37:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=43419141</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=43419141</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43419141</guid></item><item><title><![CDATA[New comment by elpalek in "Building Effective "Agents""]]></title><description><![CDATA[
<p>Claude api lacks structured output, without uniformity in output, it's not useful as agent. I've had agents system broke down suddenly due to degradation in output, which leads to the previous suggested json output hacks (from official cookbook) stopped working.</p>
]]></description><pubDate>Fri, 20 Dec 2024 23:24:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=42476147</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=42476147</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42476147</guid></item><item><title><![CDATA[New comment by elpalek in "Show HN: I wrote an open-source browser alternative for Computer Use for any LLM"]]></title><description><![CDATA[
<p>Tried Agent-E, like the DOM distillation to reduce token method. I've started using AgentQL for a new project, which works well combining playwright.</p>
]]></description><pubDate>Thu, 07 Nov 2024 04:56:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=42073537</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=42073537</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42073537</guid></item><item><title><![CDATA[New comment by elpalek in "Show HN: I Built a Rock, Paper, Scissors roguelike in React"]]></title><description><![CDATA[
<p>```
GET <a href="https://localhost:3001/socket.io/?EIO=4&transport=polling&t=PBg5rLX" rel="nofollow">https://localhost:3001/socket.io/?EIO=4&transport=polling&t=...</a> net::ERR_CONNECTION_REFUSED
```<p>Looks like you should set a production ENV?</p>
]]></description><pubDate>Fri, 01 Nov 2024 23:38:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=42022669</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=42022669</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42022669</guid></item><item><title><![CDATA[New comment by elpalek in "Ask HN: What Are You Working On? (October 2024)"]]></title><description><![CDATA[
<p>Lots of different projects. Recently finished:
beatcode: <a href="https://github.com/yudataguy/beatcode">https://github.com/yudataguy/beatcode</a><p>this is built w/ the help of claude 3.5 sonnet (new) and cursor. The idea came from want to space repetition memorization for leetcode.</p>
]]></description><pubDate>Mon, 28 Oct 2024 04:11:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=41967817</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=41967817</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41967817</guid></item><item><title><![CDATA[New comment by elpalek in "Comparing our Rust-based indexing and querying pipeline to Langchain"]]></title><description><![CDATA[
<p>Langchain and other frameworks are too bloated, it's good for demo, but highly recommend to build your own pipeline in production, it's not really that complicated, and you can have much better control over implementation. Plus you don't need 99% packages that comes with Langchain, reduce security vulnerabilities.<p>I've written a series of RAG notebooks on how to implement RAG in python directly, with minimal packages. I know it's not in Rust or C++, but it can give you some ideas on how to do things directly.<p><a href="https://github.com/yudataguy/RawRAG">https://github.com/yudataguy/RawRAG</a></p>
]]></description><pubDate>Tue, 01 Oct 2024 17:43:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=41711679</link><dc:creator>elpalek</dc:creator><comments>https://news.ycombinator.com/item?id=41711679</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41711679</guid></item></channel></rss>