<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: mehmetkeremmtl</title><link>https://news.ycombinator.com/user?id=mehmetkeremmtl</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 13 Jun 2026 16:29:36 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=mehmetkeremmtl" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by mehmetkeremmtl in "Dirty Frag: Universal Linux LPE"]]></title><description><![CDATA[
<p>With a name like 'Dirty Frag', I'm guessing this is another memory fragmentation or page cache trick similar to Dirty Pipe?</p>
]]></description><pubDate>Thu, 07 May 2026 20:00:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=48054109</link><dc:creator>mehmetkeremmtl</dc:creator><comments>https://news.ycombinator.com/item?id=48054109</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48054109</guid></item><item><title><![CDATA[New comment by mehmetkeremmtl in "Show HN: Upskill – skill to find skills for your AI agents"]]></title><description><![CDATA[
<p>Interesting approach to the dynamic skill problem. I'm curious about the overhead. How much latency does the semantic search step usually add before the agent actually executes the task?</p>
]]></description><pubDate>Wed, 06 May 2026 19:28:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=48040559</link><dc:creator>mehmetkeremmtl</dc:creator><comments>https://news.ycombinator.com/item?id=48040559</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48040559</guid></item><item><title><![CDATA[New comment by mehmetkeremmtl in "Show HN: Tilde.run – Agent sandbox with a transactional, versioned filesystem"]]></title><description><![CDATA[
<p>The versioned filesystem is exactly what's missing when agents hallucinate and go off the rails. How fast are the rollbacks if an agent completely messes up the directory state?</p>
]]></description><pubDate>Wed, 06 May 2026 19:24:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=48040512</link><dc:creator>mehmetkeremmtl</dc:creator><comments>https://news.ycombinator.com/item?id=48040512</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48040512</guid></item><item><title><![CDATA[New comment by mehmetkeremmtl in "Show HN: Hydra – Never stop coding when your AI CLI hits a rate limit"]]></title><description><![CDATA[
<p>I’ve been relying heavily on tools like Claude Code for building out my SaaS, and hitting a rate limit right in the middle of a complex debugging session is the wprst thing.<p>The 'copy context to clipboard' workaround is such a pragmatic, solution for switching CLIs. Congrats!</p>
]]></description><pubDate>Wed, 22 Apr 2026 12:11:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=47862457</link><dc:creator>mehmetkeremmtl</dc:creator><comments>https://news.ycombinator.com/item?id=47862457</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47862457</guid></item><item><title><![CDATA[New comment by mehmetkeremmtl in "Show HN: VidStudio, a browser based video editor that doesn't upload your files"]]></title><description><![CDATA[
<p>Running FFmpeg via WebAssembly and rendering with Pixi.js sounds heavy for mobile browsers, which are notoriously aggressive with memory limits. How are you handling OOM crashes or storage quota limits in IndexedDB when users import large 4K video files on mobile?</p>
]]></description><pubDate>Wed, 22 Apr 2026 12:08:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=47862426</link><dc:creator>mehmetkeremmtl</dc:creator><comments>https://news.ycombinator.com/item?id=47862426</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47862426</guid></item></channel></rss>