<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: DavidPP</title><link>https://news.ycombinator.com/user?id=DavidPP</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 19 Oct 2026 15:30:17 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=DavidPP" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by DavidPP in "Crush: Glamourous AI coding agent for your favourite terminal"]]></title><description><![CDATA[
<p>Quick correction, from what I understand Dax and Adam started from scratch for the new version.</p>
]]></description><pubDate>Thu, 31 Jul 2025 14:13:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=44745872</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=44745872</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44745872</guid></item><item><title><![CDATA[New comment by DavidPP in "Show HN: Morphik – Open-source RAG that understands PDF images, runs locally"]]></title><description><![CDATA[
<p>I'm currently building an internal tool using SurrealDB directly, but I'm curious to use Morphik since it implement features I hadn't the time to figure out yet. (For example, I started with hardcoded schemas and I like how you support both).<p>Minor nitpick, but the README for your ui-component project under ee says:<p>"License  
This project is part of Morphik and is licensed under the MIT License."<p>However, your ee folder has an "enterprise" license, not the MIT license.</p>
]]></description><pubDate>Tue, 22 Apr 2025 17:21:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=43764374</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=43764374</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43764374</guid></item><item><title><![CDATA[New comment by DavidPP in "Everything wrong with MCP"]]></title><description><![CDATA[
<p>In which client and with which LLM are you using it?<p>I use it in Claude Desktop for the right use case, it's much better than thinking mode.<p>But, I admit, I haven't tried it in Cursor or with other LLMs yet.</p>
]]></description><pubDate>Mon, 14 Apr 2025 15:50:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=43682647</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=43682647</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43682647</guid></item><item><title><![CDATA[New comment by DavidPP in "Show HN: OpenNutrition – A free, public nutrition database"]]></title><description><![CDATA[
<p>Are you using Typesense for the search server? If so, are  you using hybrid search with embeddings, or just regular search?</p>
]]></description><pubDate>Thu, 03 Apr 2025 17:29:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=43572870</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=43572870</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43572870</guid></item><item><title><![CDATA[New comment by DavidPP in "Show HN: Codemcp – Claude Code for Claude Pro subscribers – ditch API bills"]]></title><description><![CDATA[
<p>Goose from Block is also a client that supports MCP. 
 It can be used both with UI or as a CLI: <a href="https://block.github.io/goose/" rel="nofollow">https://block.github.io/goose/</a></p>
]]></description><pubDate>Thu, 20 Mar 2025 12:10:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=43422038</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=43422038</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43422038</guid></item><item><title><![CDATA[New comment by DavidPP in "Hacking Your Own AI Coding Assistant with Claude Pro and MCP"]]></title><description><![CDATA[
<p>On my end, I use <a href="https://github.com/skydeckai/mcp-server-aidd" rel="nofollow">https://github.com/skydeckai/mcp-server-aidd</a>, which has<p>-  File manipulation
-  Directory manipulation
-  tree-sitter integration<p>and more.<p>I also installed Tavily Search, sequential thinking, and Playwright.<p>I still use Cursor for development, and I use Claude Desktop for higher-level documentation, testing, etc.<p>For example, I'll check out a new repo that is lacking in documentation. I'll get the app running, then explain to Claude where the code lives, how to access the real app, and how I want the features documented.<p>Then Claude will happily scan the codebase, take screenshots of the running app, etc., all by himself, and then create a report (through the artifact system) with visualizations, graphs, etc.</p>
]]></description><pubDate>Wed, 19 Mar 2025 15:34:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=43413408</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=43413408</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43413408</guid></item><item><title><![CDATA[New comment by DavidPP in "Show HN: In-Browser Graph RAG with Kuzu-WASM and WebLLM"]]></title><description><![CDATA[
<p>I'm new to the world of graph, and I just started building with SurrealDB in embedded mode.<p>If you don't mind taking a few minutes, what are the main reasons to use Kuzu instead?</p>
]]></description><pubDate>Mon, 10 Mar 2025 23:12:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=43327239</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=43327239</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43327239</guid></item><item><title><![CDATA[Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.emergent-misalignment.com">https://www.emergent-misalignment.com</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43180322">https://news.ycombinator.com/item?id=43180322</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 26 Feb 2025 03:35:45 +0000</pubDate><link>https://www.emergent-misalignment.com</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=43180322</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43180322</guid></item><item><title><![CDATA[New comment by DavidPP in "Claude 3.7 Sonnet and Claude Code"]]></title><description><![CDATA[
<p>Haven't had time to try it out, but I've built myself a tool to tag my bookmarks and it uses 3.5 Haiku. Here is what it said about the official article content:<p><i>I apologize, but the URL and page description you provided appear to be fictional. There is no current announcement of a Claude 3.7 Sonnet model on Anthropic's website. The most recent Claude 3 models are Claude 3 Haiku, Sonnet, and Opus, released in March 2024. I cannot generate a description for a non-existent product announcement.</i><p>I appreciate their stance on safety, but that still made me laugh.</p>
]]></description><pubDate>Mon, 24 Feb 2025 19:21:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=43163719</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=43163719</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43163719</guid></item><item><title><![CDATA[New comment by DavidPP in "The benefits of learning in public"]]></title><description><![CDATA[
<p>Thanks for taking the time to explain your process.  I'm just starting out, and so far I was planning to:<p>-  Radar: just cool categorized articles, libraries, apps, etc. that I found during the week and organized in weekly drops.<p>-  Guides: In my mind, those were closer to TIL than real guides, though I couldn't figure out how to name them. I love TIL for that.<p>-  Playground: Forcing myself to share prototypes, snippets, etc.<p>I also have tons of LLM chats that could become content. Instead of trying to rewrite them, I will just share them as they are (while being transparent).<p>The main idea, as you said, is to find a modality that works well for me and force myself to write more.</p>
]]></description><pubDate>Mon, 24 Feb 2025 13:49:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=43159524</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=43159524</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43159524</guid></item><item><title><![CDATA[New comment by DavidPP in "Ask HN: What are you working on? (February 2025)"]]></title><description><![CDATA[
<p>1. My personal website. -> I spent so much time ingesting content, I finally realized I need to produce some too.<p>2. A AI assisted brief generator -> clients often have a hard time articulating their requirements for new projects.<p>3. Prototyping the UX of "my" version of the perfect "process aware" editor. More organized than a Wiki, more flexible than tools like Jira, Aha and all. Not ready to share a public link yet.  My goal is share my mockup in a week or two.</p>
]]></description><pubDate>Mon, 24 Feb 2025 13:40:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=43159426</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=43159426</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43159426</guid></item><item><title><![CDATA[New comment by DavidPP in "Understanding the BM25 full text search algorithm"]]></title><description><![CDATA[
<p>We use <a href="https://typesense.org/" rel="nofollow">https://typesense.org/</a> for regular search, but it now has support for doing hybrid search, curious if anyone has tried it yet?</p>
]]></description><pubDate>Wed, 20 Nov 2024 14:02:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=42194005</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=42194005</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42194005</guid></item><item><title><![CDATA[New comment by DavidPP in "Why does everyone run ancient Postgres versions?"]]></title><description><![CDATA[
<p>Thanks for the link, wasn't aware of this solution.</p>
]]></description><pubDate>Fri, 18 Oct 2024 17:34:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=41881649</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=41881649</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41881649</guid></item><item><title><![CDATA[Linus (Tech Tips) Meets Jim Keller (Full Interview) [video]]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.youtube.com/watch?v=rfFuTgnvwgs">https://www.youtube.com/watch?v=rfFuTgnvwgs</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=40162617">https://news.ycombinator.com/item?id=40162617</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 25 Apr 2024 20:30:22 +0000</pubDate><link>https://www.youtube.com/watch?v=rfFuTgnvwgs</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=40162617</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40162617</guid></item><item><title><![CDATA[New comment by DavidPP in "Launch HN: Creo (YC W24) – Build internal tools with NextJS and AI"]]></title><description><![CDATA[
<p>We currently using <a href="https://refine.dev/">https://refine.dev/</a> with NextJS and Material UI for a CRUD type project. How would you compare yourself to Refine?</p>
]]></description><pubDate>Tue, 02 Apr 2024 17:12:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=39908221</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=39908221</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39908221</guid></item><item><title><![CDATA[Fabric is an open-source framework for augmenting humans using AI]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/danielmiessler/fabric">https://github.com/danielmiessler/fabric</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=39681414">https://news.ycombinator.com/item?id=39681414</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 12 Mar 2024 16:28:43 +0000</pubDate><link>https://github.com/danielmiessler/fabric</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=39681414</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39681414</guid></item><item><title><![CDATA[New comment by DavidPP in "Gitlab to lay off 7% of staff"]]></title><description><![CDATA[
<p>Same here situation here (went from paid to free for a similar reason).  We are a small team, so we don't represent a lot of $, but it's changed how I perceive Gitlab as a company, and it also means I won't recommend them anymore to clients.</p>
]]></description><pubDate>Thu, 09 Feb 2023 15:58:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=34725909</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=34725909</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34725909</guid></item><item><title><![CDATA[New comment by DavidPP in "Write admin tools from day one (2022)"]]></title><description><![CDATA[
<p>I've been playing around with <a href="https://directus.io/" rel="nofollow">https://directus.io/</a> the last few weeks.<p>I'm really impressed so far, it can either act as the only backend, or as an admin tool over an existing DB.  It also has built-in support for "flows" to automate support tasks.</p>
]]></description><pubDate>Fri, 13 Jan 2023 14:04:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=34367874</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=34367874</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34367874</guid></item><item><title><![CDATA[New comment by DavidPP in "Ask HN: Can you crowdfund the compute for GPT?"]]></title><description><![CDATA[
<p>Funny, I was asking myself the same question this morning, I was wondering if there was the equivalent of SETI@Home but to pool resources for model training.</p>
]]></description><pubDate>Thu, 12 Jan 2023 14:14:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=34353746</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=34353746</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34353746</guid></item><item><title><![CDATA[New comment by DavidPP in "The state of Flow-based Programming"]]></title><description><![CDATA[
<p>Node-RED is also fairly popular in home automation circles, but it's a generic tool that can be used for different purposes.<p>For example, it can also be used to build chatbots.<p><a href="https://nodered.org/" rel="nofollow">https://nodered.org/</a></p>
]]></description><pubDate>Mon, 29 Aug 2022 13:13:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=32637781</link><dc:creator>DavidPP</dc:creator><comments>https://news.ycombinator.com/item?id=32637781</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=32637781</guid></item></channel></rss>