<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: 18Deepnar</title><link>https://news.ycombinator.com/user?id=18Deepnar</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 29 Oct 2026 20:37:18 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=18Deepnar" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by 18Deepnar in "Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5"]]></title><description><![CDATA[
<p>why do i not see as much traction and stirring up on the internet for gemini models as much as claude or gpt even though on bench's they are very much THE frontier. is the reason very limited access early or or just not enough publicity or hype as the other labs do?</p>
]]></description><pubDate>Thu, 29 Oct 2026 14:33:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=50289764</link><dc:creator>18Deepnar</dc:creator><comments>https://news.ycombinator.com/item?id=50289764</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50289764</guid></item><item><title><![CDATA[New comment by 18Deepnar in "Show HN: Google, Outlook and iCloud in one superpowered calendar"]]></title><description><![CDATA[
<p>hey i loved the idea of it being centralized and the mcp to get connected to our own subcription, but what about the local use of it with local ai, also something more than a calendar but more like a P.A. for like making my daily plan for the weeks?</p>
]]></description><pubDate>Wed, 14 Oct 2026 12:36:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=50086742</link><dc:creator>18Deepnar</dc:creator><comments>https://news.ycombinator.com/item?id=50086742</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50086742</guid></item><item><title><![CDATA[New comment by 18Deepnar in "Intelligence per Watt: Measuring Intelligence Efficiency of Local AI"]]></title><description><![CDATA[
<p>yea i see the potential of local slms too, it wont replace the frontier llms but for particular aspects they are generally really good, and at a certain point models like qwen 3.8 if people are able to set up proper api providers for it it can be extremely cheap and helpful. I am also working on trying to fix the memory and low context issue of such slms so they can actually be used locally for real use cases and not just small work</p>
]]></description><pubDate>Thu, 17 Sep 2026 08:55:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=49738120</link><dc:creator>18Deepnar</dc:creator><comments>https://news.ycombinator.com/item?id=49738120</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49738120</guid></item><item><title><![CDATA[New comment by 18Deepnar in "Ubuntu 26.10 completes transition to Rust-based coreutils"]]></title><description><![CDATA[
<p>how helpful is it for it to be transitioned to rust, how does it help?</p>
]]></description><pubDate>Tue, 15 Sep 2026 09:47:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=49710012</link><dc:creator>18Deepnar</dc:creator><comments>https://news.ycombinator.com/item?id=49710012</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49710012</guid></item></channel></rss>