<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: DSemba</title><link>https://news.ycombinator.com/user?id=DSemba</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 03 Jul 2026 07:51:20 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=DSemba" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Lawsuit alleges Samsung, SK Hynix, and Micron colluded to inflate DRAM prices]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.polygon.com/ram-manufacturers-sued-supply-price-fixing/">https://www.polygon.com/ram-manufacturers-sued-supply-price-fixing/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48754005">https://news.ycombinator.com/item?id=48754005</a></p>
<p>Points: 7</p>
<p># Comments: 1</p>
]]></description><pubDate>Wed, 01 Jul 2026 22:30:26 +0000</pubDate><link>https://www.polygon.com/ram-manufacturers-sued-supply-price-fixing/</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=48754005</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48754005</guid></item><item><title><![CDATA[Moebius: 0.2B image inpainting model with 10B-level performance]]></title><description><![CDATA[
<p>Article URL: <a href="https://hustvl.github.io/Moebius/">https://hustvl.github.io/Moebius/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48630171">https://news.ycombinator.com/item?id=48630171</a></p>
<p>Points: 322</p>
<p># Comments: 83</p>
]]></description><pubDate>Mon, 22 Jun 2026 13:53:02 +0000</pubDate><link>https://hustvl.github.io/Moebius/</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=48630171</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48630171</guid></item><item><title><![CDATA[New comment by DSemba in "Now AI agents need what RSS does"]]></title><description><![CDATA[
<p>I'd argue LLMs are getting cheaper, so it will get more feasible for LLMs to soon act on our behalf, bringing only what we're interested in.<p>Projects like OpenClaw and Hermes already show that this can work whether the source is RSS or simply a website the agent visits.<p>Even Google now envisions this, since they recently announced "information agents" (<a href="https://blog.google/products-and-platforms/products/search/search-io-2026/" rel="nofollow">https://blog.google/products-and-platforms/products/search/s...</a>) that will keep working in the background.
They surely have an index they can use, but I wonder whether that's necessary?  AI agents like Claude Code suggest it's possible to use simple keyword searches, without maintaining vector indexes - <a href="https://www.tigerdata.com/blog/why-cursor-is-about-to-ditch-vector-search-and-you-should-too" rel="nofollow">https://www.tigerdata.com/blog/why-cursor-is-about-to-ditch-...</a><p>It could be that soon we're gonna get a fully personalized briefing on the topics that we're interested in, or maybe a new kind of feed, replacing social media.<p>I'm actually working on the briefing idea myself: <a href="https://briefin.com" rel="nofollow">https://briefin.com</a></p>
]]></description><pubDate>Wed, 03 Jun 2026 10:53:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=48382314</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=48382314</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48382314</guid></item><item><title><![CDATA[New comment by DSemba in "Turn Hacker News into a personalized brief"]]></title><description><![CDATA[
<p>Thanks :) Each brief brings the stories in the format shown on the page.<p>I myself tried n8n in the beginning but these workflows get pretty complex pretty quickly.</p>
]]></description><pubDate>Thu, 28 May 2026 16:53:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=48311724</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=48311724</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48311724</guid></item><item><title><![CDATA[Turn Hacker News into a personalized brief]]></title><description><![CDATA[
<p>Article URL: <a href="https://briefin.com/hackernews/">https://briefin.com/hackernews/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48310757">https://news.ycombinator.com/item?id=48310757</a></p>
<p>Points: 4</p>
<p># Comments: 2</p>
]]></description><pubDate>Thu, 28 May 2026 15:53:57 +0000</pubDate><link>https://briefin.com/hackernews/</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=48310757</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48310757</guid></item><item><title><![CDATA[New comment by DSemba in "Hacker News front page as a site"]]></title><description><![CDATA[
<p>I actually recently submitted something similar - <a href="https://briefin.com/hackernews/" rel="nofollow">https://briefin.com/hackernews/</a><p>Less like good-old newspaper, but instead made for scannability & readability, with discussion highlights for each story.<p>Any feedback greatly appreciated!</p>
]]></description><pubDate>Tue, 26 May 2026 16:01:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=48281558</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=48281558</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48281558</guid></item><item><title><![CDATA[New comment by DSemba in "Best "Brain" for Agents Is Just Versioned Folders of Markdown Files"]]></title><description><![CDATA[
<p>I once made a slide deck on vector vs keyword search, right when vector dbs were on the rise:<p><a href="https://vec3.ai/" rel="nofollow">https://vec3.ai/</a><p>Seeing the confusion this article caused maybe someone will find it useful.</p>
]]></description><pubDate>Fri, 15 May 2026 11:16:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=48147194</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=48147194</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48147194</guid></item><item><title><![CDATA[New comment by DSemba in "Best "Brain" for Agents Is Just Versioned Folders of Markdown Files"]]></title><description><![CDATA[
<p>I see the authors don't argue it well enough, but one could use AI agents with simple grep and that proved to be efficient enough to be the default in Claude Code.<p>I personally turned of indexing feature in Cursor and I use it without it - I haven't noticed any accuracy drop, though my codebase is not enterprise-size one.</p>
]]></description><pubDate>Fri, 15 May 2026 11:13:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=48147173</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=48147173</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48147173</guid></item><item><title><![CDATA[New comment by DSemba in "Ask HN: What are you working on? (May 2026)"]]></title><description><![CDATA[
<p>I'm working on <a href="https://briefin.com/" rel="nofollow">https://briefin.com/</a>, which turns any topic into a newsletter.<p>I wanted to replace those passive social media feeds, where I'm just being served what gets clicks. I completely avoided any embeddings or typical rankings, using ai agents instead, to get precise results and things that are actually interesting to me.<p>Still working on the platform, but I made a tool that already turns Hacker News into a personalized daily digest here <a href="https://briefin.com/hackernews/" rel="nofollow">https://briefin.com/hackernews/</a> (with summaries of the discussions)<p>Let me know what you think :)</p>
]]></description><pubDate>Mon, 11 May 2026 02:34:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=48090452</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=48090452</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48090452</guid></item><item><title><![CDATA[New comment by DSemba in "87.7% of entrepreneurs struggle with at least one mental health issue"]]></title><description><![CDATA[
<p>On the other hand, NIMH says 31.1% of U.S. adults have anxiety <a href="https://www.nimh.nih.gov/health/statistics/any-anxiety-disorder" rel="nofollow">https://www.nimh.nih.gov/health/statistics/any-anxiety-disor...</a></p>
]]></description><pubDate>Thu, 02 May 2024 20:02:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=40240800</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=40240800</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40240800</guid></item><item><title><![CDATA[Race to build AI software engineers]]></title><description><![CDATA[
<p>Article URL: <a href="https://dariuszsemba.com/blog/race-to-build-ai-software-engineers/">https://dariuszsemba.com/blog/race-to-build-ai-software-engineers/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=39996759">https://news.ycombinator.com/item?id=39996759</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 10 Apr 2024 23:29:03 +0000</pubDate><link>https://dariuszsemba.com/blog/race-to-build-ai-software-engineers/</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=39996759</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39996759</guid></item><item><title><![CDATA[New comment by DSemba in "Beyond VC-funded Evangelism: The Case Against Vector Databases"]]></title><description><![CDATA[
<p>at least you know a human wrote it :)</p>
]]></description><pubDate>Thu, 16 Nov 2023 09:12:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=38287254</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=38287254</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38287254</guid></item><item><title><![CDATA[Beyond VC-funded Evangelism: The Case Against Vector Databases]]></title><description><![CDATA[
<p>Article URL: <a href="https://vec3.ai">https://vec3.ai</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=38281923">https://news.ycombinator.com/item?id=38281923</a></p>
<p>Points: 2</p>
<p># Comments: 2</p>
]]></description><pubDate>Wed, 15 Nov 2023 20:22:48 +0000</pubDate><link>https://vec3.ai</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=38281923</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38281923</guid></item><item><title><![CDATA[Why AutoGPT engineers ditched vector databases]]></title><description><![CDATA[
<p>Article URL: <a href="https://dariuszsemba.com/blog/why-autogpt-engineers-ditched-vector-databases/">https://dariuszsemba.com/blog/why-autogpt-engineers-ditched-vector-databases/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=37825155">https://news.ycombinator.com/item?id=37825155</a></p>
<p>Points: 109</p>
<p># Comments: 58</p>
]]></description><pubDate>Mon, 09 Oct 2023 20:34:05 +0000</pubDate><link>https://dariuszsemba.com/blog/why-autogpt-engineers-ditched-vector-databases/</link><dc:creator>DSemba</dc:creator><comments>https://news.ycombinator.com/item?id=37825155</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37825155</guid></item></channel></rss>