<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: maxlegav</title><link>https://news.ycombinator.com/user?id=maxlegav</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 06 May 2026 16:09:39 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=maxlegav" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by maxlegav in "Show HN: Pyra – a Python toolchain experiment inspired by uv and Bun"]]></title><description><![CDATA[
<p>I have seen the comments, maybe you could provide a real use case that we maybe did not think about.</p>
]]></description><pubDate>Mon, 20 Apr 2026 11:43:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=47832891</link><dc:creator>maxlegav</dc:creator><comments>https://news.ycombinator.com/item?id=47832891</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47832891</guid></item><item><title><![CDATA[New comment by maxlegav in "Show HN: Gave Claude a casino bankroll – it gambles till it's too broke to think"]]></title><description><![CDATA[
<p>Really interesting but is there a chance/way to actually win or is it losed forced. I think it would be a great sandbox for prompts test to see which strategy you can use to make the model more responsible.</p>
]]></description><pubDate>Mon, 20 Apr 2026 11:37:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=47832841</link><dc:creator>maxlegav</dc:creator><comments>https://news.ycombinator.com/item?id=47832841</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47832841</guid></item><item><title><![CDATA[New comment by maxlegav in "Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)"]]></title><description><![CDATA[
<p>Do you see a real difference with AI agents working together</p>
]]></description><pubDate>Mon, 20 Apr 2026 11:29:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=47832793</link><dc:creator>maxlegav</dc:creator><comments>https://news.ycombinator.com/item?id=47832793</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47832793</guid></item><item><title><![CDATA[New comment by maxlegav in "Show HN: Mcptube – Karpathy's LLM Wiki idea applied to YouTube videos"]]></title><description><![CDATA[
<p>Great let me know to try it !</p>
]]></description><pubDate>Mon, 20 Apr 2026 11:26:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=47832772</link><dc:creator>maxlegav</dc:creator><comments>https://news.ycombinator.com/item?id=47832772</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47832772</guid></item><item><title><![CDATA[New comment by maxlegav in "Algebrica: A Mathematical Knowledge Base"]]></title><description><![CDATA[
<p>The ontological graph is a great idea a giant mental map helps a lot, but it would be even better if it were interactive. Giving people a path to actually understand where to start. I think using AI where you describe your country, the grade you're in, etc... would be a great use of AI for once :)</p>
]]></description><pubDate>Tue, 14 Apr 2026 12:16:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=47764620</link><dc:creator>maxlegav</dc:creator><comments>https://news.ycombinator.com/item?id=47764620</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47764620</guid></item><item><title><![CDATA[New comment by maxlegav in "Show HN: Early Reader – Free open source reading app I built for my 4-year-old"]]></title><description><![CDATA[
<p>Looks great, I vibe coded something similar myself because everything I have seen is really expensive. I actually went through your repo on GitHub and really like the local-first approach with SQLite and pre-generated assets.But with ~4k audio files and 721 cards, how are you handling app size and load times on mobile? Did you run into any constraints there or have to optimize asset loading in a specific way?</p>
]]></description><pubDate>Tue, 14 Apr 2026 12:02:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=47764502</link><dc:creator>maxlegav</dc:creator><comments>https://news.ycombinator.com/item?id=47764502</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47764502</guid></item><item><title><![CDATA[New comment by maxlegav in "Show HN: Mcptube – Karpathy's LLM Wiki idea applied to YouTube videos"]]></title><description><![CDATA[
<p>Hi, do you plan to add some other endpoint like a summarize content video? Great project currently trying the MCP.</p>
]]></description><pubDate>Tue, 14 Apr 2026 11:49:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=47764390</link><dc:creator>maxlegav</dc:creator><comments>https://news.ycombinator.com/item?id=47764390</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47764390</guid></item></channel></rss>