<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: dh1011</title><link>https://news.ycombinator.com/user?id=dh1011</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 25 Apr 2026 10:52:14 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=dh1011" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by dh1011 in "Website streamed live directly from a model"]]></title><description><![CDATA[
<p>Very cool idea. Wish it could render faster.</p>
]]></description><pubDate>Wed, 22 Apr 2026 22:17:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=47870016</link><dc:creator>dh1011</dc:creator><comments>https://news.ycombinator.com/item?id=47870016</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47870016</guid></item><item><title><![CDATA[New comment by dh1011 in "I run multiple $10K MRR companies on a $20/month tech stack"]]></title><description><![CDATA[
<p>> If you have a graphics card sitting somewhere in your house, you already have unlimited AI credits.<p>I tried running a local LLM, and it’s actually cheaper to use AI credits when you factor in electricity costs. Only use a local LLM if data privacy is your priority.</p>
]]></description><pubDate>Sun, 12 Apr 2026 22:01:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=47745028</link><dc:creator>dh1011</dc:creator><comments>https://news.ycombinator.com/item?id=47745028</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47745028</guid></item><item><title><![CDATA[New comment by dh1011 in "AniSora: Open-source anime video generation model"]]></title><description><![CDATA[
<p><a href="https://huggingface.co/IndexTeam/Index-anisora" rel="nofollow">https://huggingface.co/IndexTeam/Index-anisora</a></p>
]]></description><pubDate>Sun, 18 May 2025 00:20:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=44018003</link><dc:creator>dh1011</dc:creator><comments>https://news.ycombinator.com/item?id=44018003</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44018003</guid></item><item><title><![CDATA[New comment by dh1011 in "Ask HN: What are you working on? (April 2025)"]]></title><description><![CDATA[
<p><a href="https://github.com/dh1011/c2p">https://github.com/dh1011/c2p</a><p><a href="https://marketplace.visualstudio.com/items?itemName=H337.c2p" rel="nofollow">https://marketplace.visualstudio.com/items?itemName=H337.c2p</a><p>I’m developing a VS Code and Cursor extension that helps developers quickly copy all code in a workspace to the clipboard for use with LLMs.<p>It also displays the token count for each file, as well as the total token count across the workspace.<p>By default, it ignores files listed in .gitignore, but this behavior can be customized in the extension settings, along with many other options.</p>
]]></description><pubDate>Mon, 28 Apr 2025 22:19:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=43826738</link><dc:creator>dh1011</dc:creator><comments>https://news.ycombinator.com/item?id=43826738</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43826738</guid></item><item><title><![CDATA[New comment by dh1011 in ".localhost Domains"]]></title><description><![CDATA[
<p>Thanks for sharing!<p>This is cool, but it only seems to work on the host that has the /etc/hosts loopback redirect to *.localhost. I run my app on a home server and access it from multiple PCs on the LAN. I have several apps, each associated with a different port number. Right now, I rely on a start page (<a href="https://github.com/dh1011/start-ichi">https://github.com/dh1011/start-ichi</a>) to keep track of all those ports. I’m wondering if there’s an easy way to resolve custom domains to each of those apps?</p>
]]></description><pubDate>Fri, 11 Apr 2025 06:27:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=43651034</link><dc:creator>dh1011</dc:creator><comments>https://news.ycombinator.com/item?id=43651034</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43651034</guid></item><item><title><![CDATA[New comment by dh1011 in "Ask HN: What are you working on? (March 2025)"]]></title><description><![CDATA[
<p>I'm working on a VSCode extension that lets me quickly copy code from a workspace into a structured format for LLMs.
This makes it easy to provide context so the LLM can continue developing the codebase.<p>There are other similar tools out there—mostly web apps or CLI-based—but I found a VSCode extension to be the fastest and most convenient option for VSCode users.<p>Here’s the extension link: <a href="https://marketplace.visualstudio.com/items?itemName=H337.c2p" rel="nofollow">https://marketplace.visualstudio.com/items?itemName=H337.c2p</a><p>I'd love to get any feedback.</p>
]]></description><pubDate>Mon, 31 Mar 2025 03:34:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=43530625</link><dc:creator>dh1011</dc:creator><comments>https://news.ycombinator.com/item?id=43530625</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43530625</guid></item><item><title><![CDATA[Show HN: C2p – VS Code Extension to Quickly Copy Codebase into a Prompt]]></title><description><![CDATA[
<p>Article URL: <a href="https://marketplace.visualstudio.com/items?itemName=H337.c2p">https://marketplace.visualstudio.com/items?itemName=H337.c2p</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43180555">https://news.ycombinator.com/item?id=43180555</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 26 Feb 2025 04:18:53 +0000</pubDate><link>https://marketplace.visualstudio.com/items?itemName=H337.c2p</link><dc:creator>dh1011</dc:creator><comments>https://news.ycombinator.com/item?id=43180555</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43180555</guid></item><item><title><![CDATA[New comment by dh1011 in "Ask HN: Is anyone doing anything cool with tiny language models?"]]></title><description><![CDATA[
<p>I copied all the text from this post and used an LLM to generate a list of all the ideas. I do the same for other similar HN post .</p>
]]></description><pubDate>Wed, 22 Jan 2025 03:04:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=42788471</link><dc:creator>dh1011</dc:creator><comments>https://news.ycombinator.com/item?id=42788471</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42788471</guid></item><item><title><![CDATA[New comment by dh1011 in "The best browser bookmarking system is files"]]></title><description><![CDATA[
<p>I completely agree that bookmarks should prioritize content over metadata. This is actually what led me to develop the "semantic-bookmark-manager" [1]. It uses LLM to summarize the content of bookmarked pages and generate relevant tags. Additionally, it utilizes RAG to facilitate semantic searching within your bookmarks.<p>[1] <a href="https://github.com/dh1011/semantic-bookmark-manager">https://github.com/dh1011/semantic-bookmark-manager</a></p>
]]></description><pubDate>Mon, 30 Sep 2024 22:35:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=41702846</link><dc:creator>dh1011</dc:creator><comments>https://news.ycombinator.com/item?id=41702846</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41702846</guid></item><item><title><![CDATA[New comment by dh1011 in "Ask HN: What are you working on (September 2024)?"]]></title><description><![CDATA[
<p>I am working on "Subscription Manager," a simple single-page web application that allows users to manage their recurring payments. It provides a summary of your expenses, including weekly, monthly, and yearly totals for all your current subscriptions. Additionally, it features notifications through NTFY to notify when a subscription is dued for payment.<p>Here is the Github repo of this project: <a href="https://github.com/dh1011/subscription-manager">https://github.com/dh1011/subscription-manager</a><p>This is a self-hosted open-source project, licensed under the MIT license.</p>
]]></description><pubDate>Mon, 30 Sep 2024 02:43:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=41693012</link><dc:creator>dh1011</dc:creator><comments>https://news.ycombinator.com/item?id=41693012</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41693012</guid></item><item><title><![CDATA[Show HN: Semantic Bookmark Manager]]></title><description><![CDATA[
<p>Hi Hacker News,<p>I would like to share my new side project: the Semantic Bookmark Manager. This web application is designed to help users manage and semantically search for their bookmarks using the RAG technique.<p>Traditional bookmark managers can become quite disorganized and difficult to navigate as they grow. This tool offers a solution by eliminating the need for manual categorization, therefore simplifying the overall user experience.<p>It is open-source under MIT license<p>Thank you for your attention, and I hope you find it useful :)</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=41506696">https://news.ycombinator.com/item?id=41506696</a></p>
<p>Points: 5</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 10 Sep 2024 23:27:49 +0000</pubDate><link>https://github.com/dh1011/semantic-bookmark-manager</link><dc:creator>dh1011</dc:creator><comments>https://news.ycombinator.com/item?id=41506696</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41506696</guid></item><item><title><![CDATA[New comment by dh1011 in "Show HN: LLM-Term – Simple Rust-based CLI assist tool"]]></title><description><![CDATA[
<p>Thank you. I was using VHS for the demo. Here is the link: <a href="https://github.com/charmbracelet/vhs">https://github.com/charmbracelet/vhs</a></p>
]]></description><pubDate>Thu, 29 Aug 2024 15:03:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=41391532</link><dc:creator>dh1011</dc:creator><comments>https://news.ycombinator.com/item?id=41391532</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41391532</guid></item><item><title><![CDATA[Show HN: LLM-Term – Simple Rust-based CLI assist tool]]></title><description><![CDATA[
<p>Current AI-assisted CLI tools are often part of larger systems and work better on Linux. 
I built llm-term to address these. It's a Rust-based tool that compiles into a single binary file. You only need to download the binary, add it to your PATH, and configure your OpenAI key to get started.
While llm-term offers an option for gpt-4o, it works great with gpt-4o-mini. So it's not costly.
I appreciate any feedback or suggestions.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=41388335">https://news.ycombinator.com/item?id=41388335</a></p>
<p>Points: 32</p>
<p># Comments: 11</p>
]]></description><pubDate>Thu, 29 Aug 2024 07:42:45 +0000</pubDate><link>https://github.com/dh1011/llm-term</link><dc:creator>dh1011</dc:creator><comments>https://news.ycombinator.com/item?id=41388335</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41388335</guid></item></channel></rss>