<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai on ZoliBen Csupra(Kabra)</title><link>https://zoliben.com/en/tags/ai/</link><description>Recent content in Ai on ZoliBen Csupra(Kabra)</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 24 Apr 2026 12:00:00 +0000</lastBuildDate><atom:link href="https://zoliben.com/en/tags/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Memorito — Personal Knowledge Base with Automated Search</title><link>https://zoliben.com/en/posts/2026-04-24-memorito-personal-knowledge-base-with-automated-search/</link><pubDate>Fri, 24 Apr 2026 12:00:00 +0000</pubDate><guid>https://zoliben.com/en/posts/2026-04-24-memorito-personal-knowledge-base-with-automated-search/</guid><description>&lt;p>I spent a lot of time searching the internet and realized that my personal knowledge was scattered everywhere: notes, PDFs, bookmarks, snippets, links, images, voice recordings — all in different places, never findable when I needed them. Notion was good, but I didn&amp;rsquo;t want to put my brain&amp;rsquo;s content into another SaaS service.&lt;/p>
&lt;p>Then I thought: &amp;ldquo;Why don&amp;rsquo;t I build my own?&amp;rdquo;&lt;/p>
&lt;p>And I did.&lt;/p>
&lt;h2 id="what-is-memorito">What is Memorito?&lt;/h2>
&lt;p>Memorito is a self-hosted, multimodal knowledge base that I built for myself — not a ready-made product I use, but something I coded for my own needs and continuously develop. It can process, index, and search text, URLs, images, audio files, and PDFs. Not just keyword search — semantic search, meaning it finds relevant content based on meaning.&lt;/p></description></item><item><title>Qwen 3.6: 35B vs 27B comparison - benchmark results</title><link>https://zoliben.com/en/posts/2026-04-23-qwen-36-35b-vs-27b-benchmark-results/</link><pubDate>Thu, 23 Apr 2026 12:00:00 +0000</pubDate><guid>https://zoliben.com/en/posts/2026-04-23-qwen-36-35b-vs-27b-benchmark-results/</guid><description>&lt;p>I finally summed up all the Qwen 3.6 model test results I gathered over the past few days. I compared two models in detail: the &lt;strong>Qwen3.6-35B-A3B&lt;/strong> (MoE, hybrid attention/delta) and the &lt;strong>Qwen3.6-27B&lt;/strong> (dense, hybrid attention/delta). I ran both with turbo3 KV cache compression on an RTX 4090 as a llama.cpp server.&lt;/p>
&lt;p>If I had to summarize briefly: the 35B-A3B is &lt;strong>3-4x faster&lt;/strong> in everything, but the 27B delivers &lt;strong>better quality&lt;/strong>. This is the classic MoE vs. dense tradeoff, just backed by numbers.&lt;/p></description></item><item><title>Migrating the Blog from WordPress to Hugo with OpenCode</title><link>https://zoliben.com/en/posts/2026-04-17-a-blog-atalakitasa-wordpressbol-hugoba-az-opencode-segitsegevel/</link><pubDate>Fri, 17 Apr 2026 20:00:00 +0000</pubDate><guid>https://zoliben.com/en/posts/2026-04-17-a-blog-atalakitasa-wordpressbol-hugoba-az-opencode-segitsegevel/</guid><description>&lt;p>My last post was published in March 2021, and since then, almost nothing has happened with the blog - despite moving, server changes, and numerous other developments. WordPress had been more irritating than helpful for returning to writing posts: it was slow, required constant plugin updates, and security vulnerabilities kept pouring in, while for a blog that only publishes a few posts per year, it was overly complex.&lt;/p>
&lt;p>For years I had been considering switching to a static site generator, but the thought of migration - 87 posts, lots of HTML remnants, media files - always deterred me. Then I discovered OpenCode, and everything changed.&lt;/p></description></item></channel></rss>