<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: unrahul</title><link>https://news.ycombinator.com/user?id=unrahul</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 23 Apr 2026 13:50:36 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=unrahul" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by unrahul in "Show HN: Ocrbase – pdf → .md/.json document OCR and structured extraction API"]]></title><description><![CDATA[
<p>I have seen this flow in what people in some startups call "Agentic OCR", its essentially a control flow that is coded that tries pdf-parse first or a similar non expensive approach, and if it fails a threshold then use screenshot to text extraction.</p>
]]></description><pubDate>Tue, 20 Jan 2026 18:21:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=46695699</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=46695699</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46695699</guid></item><item><title><![CDATA[New comment by unrahul in "LLMs can teach themselves to better predict the future"]]></title><description><![CDATA[
<p>Hey Danny, Really nice read.<p>Do you plan to share the source code to see if we could replicate this?</p>
]]></description><pubDate>Tue, 11 Feb 2025 18:48:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=43016618</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=43016618</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43016618</guid></item><item><title><![CDATA[New comment by unrahul in "Bypass DeepSeek censorship by speaking in hex"]]></title><description><![CDATA[
<p>We don’t want hex , can ask in a language that is not popular or the first 5 in the dataset , and it would answer , but not always will work with deep think . Using a tiny translator model in front of the api can make it more ‘open’.</p>
]]></description><pubDate>Fri, 31 Jan 2025 22:03:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=42892722</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=42892722</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42892722</guid></item><item><title><![CDATA[New comment by unrahul in "Fixing Gemma Bugs"]]></title><description><![CDATA[
<p>Daniel is of the best engineers I have ever worked with. Engineer in the true sense of wanting to know how something works and figuring out ways to improve it !</p>
]]></description><pubDate>Tue, 12 Mar 2024 07:02:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=39676863</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=39676863</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39676863</guid></item><item><title><![CDATA[New comment by unrahul in "Advent of GenAI Hackathon on Intel GPUs"]]></title><description><![CDATA[
<p>AI Developers, Startup Founders, Students: Ready for a Challenge?
 Join the "Advent of GenAI Hackathon" by Prediction Guard, with Intel Liftoff's support. A week-long journey into Generative AI awaits, packed with daily challenges to test your skills.
 Dive Deep into LLMs and experiment hands-on with Intel Corporation's AI Developer Cloud. Experience the power of Intel Xeon CPUs and Intel Data Center GPU Max!
 Build a Jupyter Notebook-based application that could win you cloud credits and recognition.
 Enroll by Dec 2: <a href="https://adventofgenai.com" rel="nofollow noreferrer">https://adventofgenai.com</a></p>
]]></description><pubDate>Thu, 23 Nov 2023 20:44:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=38397314</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=38397314</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38397314</guid></item><item><title><![CDATA[Advent of GenAI Hackathon on Intel GPUs]]></title><description><![CDATA[
<p>Article URL: <a href="https://adventofgenai.com/">https://adventofgenai.com/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=38397313">https://news.ycombinator.com/item?id=38397313</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 23 Nov 2023 20:44:39 +0000</pubDate><link>https://adventofgenai.com/</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=38397313</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38397313</guid></item><item><title><![CDATA[New comment by unrahul in "[dead]"]]></title><description><![CDATA[
<p>I couldn't find online how to finetune LLMs on an Intel dGPU, so i made a simple version. This particular one can be used to generate text based on your favorite book (for eg). I hope you find it useful if you are having an Intel discrete GPU.</p>
]]></description><pubDate>Fri, 26 May 2023 02:38:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=36079094</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=36079094</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=36079094</guid></item><item><title><![CDATA[New comment by unrahul in "Unofficial guide to setup Intel dGPUs in Linux"]]></title><description><![CDATA[
<p>If you are one of those folks who use Linux and intel dGPUs (a tiny minority, I am sure :)) like me and is finding it difficult to set up a functional dev environment for the GPUs (Arc Alchemist, Datacenter Flex, GPU Max cards). This repo will help you set it up. I would love to get your feedback on this and on improvements that can be made. I made this for myself after I was tired of doing this many times. If there are any changes to the intel gpu docs, the repo gets auto-updated, so you can be sure this setup will work (to an extent).<p>I have also written a verification tool(<a href="https://github.com/rahulunair/xpu_verify">https://github.com/rahulunair/xpu_verify</a>) that can test if the setup is correct and help you fix it if it is not. The  verification scripts will automatically run some C++ sycl parallel programming examples, AI examples using TensorFlow and PyTorch, and a few others. I would once again greatly appreciate any feedback on this.</p>
]]></description><pubDate>Thu, 27 Apr 2023 16:17:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=35730364</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=35730364</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35730364</guid></item><item><title><![CDATA[Unofficial guide to setup Intel dGPUs in Linux]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/rahulunair/xpu_setup">https://github.com/rahulunair/xpu_setup</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=35730363">https://news.ycombinator.com/item?id=35730363</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 27 Apr 2023 16:17:08 +0000</pubDate><link>https://github.com/rahulunair/xpu_setup</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=35730363</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35730363</guid></item><item><title><![CDATA[New comment by unrahul in "Show HN: I wrote a book about using data science to solve “everyday” problems"]]></title><description><![CDATA[
<p>Congrats!<p>Really nice work, I just bought it and put in on my reading list for today</p>
]]></description><pubDate>Wed, 24 Feb 2021 23:41:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=26257752</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=26257752</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=26257752</guid></item><item><title><![CDATA[New comment by unrahul in "[dead]"]]></title><description><![CDATA[
<p>I was playing around with PyO3 and thought of building a UUID wrapper for Python using Rust's UUID library.</p>
]]></description><pubDate>Thu, 18 Feb 2021 09:57:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=26177980</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=26177980</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=26177980</guid></item><item><title><![CDATA[Show HN: An async API and a CLI tool to search YouTube without using the DataAPI]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/rahulunair/utube-search">https://github.com/rahulunair/utube-search</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=26149566">https://news.ycombinator.com/item?id=26149566</a></p>
<p>Points: 6</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 16 Feb 2021 00:28:45 +0000</pubDate><link>https://github.com/rahulunair/utube-search</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=26149566</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=26149566</guid></item><item><title><![CDATA[New comment by unrahul in "Show HN: Peek into a remote repo from GitHub or Gitlab quickly"]]></title><description><![CDATA[
<p>Also, i am looking at ways to make pulling the content the fastest way possible using cdn cached files where possible and things like that..</p>
]]></description><pubDate>Mon, 15 Feb 2021 01:36:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=26138089</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=26138089</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=26138089</guid></item><item><title><![CDATA[New comment by unrahul in "Show HN: Peek into a remote repo from GitHub or Gitlab quickly"]]></title><description><![CDATA[
<p>for the core functionality, the tool pretty much does that, although I am thinking of adding trending repos and things as such.. and any other features that other folks have in mind, keeping the core utility of the tool as opening a repo in your editor</p>
]]></description><pubDate>Mon, 15 Feb 2021 01:34:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=26138076</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=26138076</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=26138076</guid></item><item><title><![CDATA[New comment by unrahul in "Show HN: Peek into a remote repo from GitHub or Gitlab quickly"]]></title><description><![CDATA[
<p>Yup that is the intent, i designed it keeping in mind, I download very many repos and open it on vim, search is then offloaded to your tool of choice.<p>Future improvements I am looking at is to add a search for trending remote repos and some caching mechanism</p>
]]></description><pubDate>Mon, 15 Feb 2021 01:32:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=26138066</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=26138066</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=26138066</guid></item><item><title><![CDATA[Show HN: Peek into a remote repo from GitHub or Gitlab quickly]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/rahulunair/repo-peek">https://github.com/rahulunair/repo-peek</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=26129986">https://news.ycombinator.com/item?id=26129986</a></p>
<p>Points: 32</p>
<p># Comments: 10</p>
]]></description><pubDate>Sun, 14 Feb 2021 05:39:17 +0000</pubDate><link>https://github.com/rahulunair/repo-peek</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=26129986</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=26129986</guid></item><item><title><![CDATA[New comment by unrahul in "Show HN: GitHub-peek – quickly peek a remote repo locally in ur favorite editor"]]></title><description><![CDATA[
<p>With github1s getting released last week, I have seen a few implementations that help in quickly viewing a remote codebase. This is my attempt to build one, the tool pulls a remote repo locally and opens it in your favorite editor. It takes care of deleting the repo after you close your editor as well.</p>
]]></description><pubDate>Sat, 13 Feb 2021 02:56:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=26120991</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=26120991</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=26120991</guid></item><item><title><![CDATA[Show HN: GitHub-peek – quickly peek a remote repo locally in ur favorite editor]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/rahulunair/github-peek">https://github.com/rahulunair/github-peek</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=26120990">https://news.ycombinator.com/item?id=26120990</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Sat, 13 Feb 2021 02:56:29 +0000</pubDate><link>https://github.com/rahulunair/github-peek</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=26120990</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=26120990</guid></item><item><title><![CDATA[The Evolution of the Unix Time Sharing System [pdf]]]></title><description><![CDATA[
<p>Article URL: <a href="http://www.read.seas.harvard.edu/~kohler/class/aosref/ritchie84evolution.pdf">http://www.read.seas.harvard.edu/~kohler/class/aosref/ritchie84evolution.pdf</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=14023015">https://news.ycombinator.com/item?id=14023015</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 03 Apr 2017 14:33:40 +0000</pubDate><link>http://www.read.seas.harvard.edu/~kohler/class/aosref/ritchie84evolution.pdf</link><dc:creator>unrahul</dc:creator><comments>https://news.ycombinator.com/item?id=14023015</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=14023015</guid></item></channel></rss>