<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: Primer81</title><link>https://news.ycombinator.com/user?id=Primer81</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 24 Oct 2026 14:07:38 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=Primer81" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by Primer81 in "Every AI model has the same "controversial" take on humans"]]></title><description><![CDATA[
<p>My first thought as well. I personally don't find these types of "studies" very interesting, but I assume I'm not the target audience. For someone not well exposed to AI, it might be interesting.</p>
]]></description><pubDate>Thu, 22 Oct 2026 17:26:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=50198400</link><dc:creator>Primer81</dc:creator><comments>https://news.ycombinator.com/item?id=50198400</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50198400</guid></item><item><title><![CDATA[New comment by Primer81 in "Crystal 1.22"]]></title><description><![CDATA[
<p>what does this language excel at in particular? havent heard of it before and didnt find a clear use case / mission statement on the webpage. unless I'm missing where to find it. just curious to learn more.</p>
]]></description><pubDate>Thu, 22 Oct 2026 14:24:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=50195837</link><dc:creator>Primer81</dc:creator><comments>https://news.ycombinator.com/item?id=50195837</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50195837</guid></item><item><title><![CDATA[New comment by Primer81 in "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"]]></title><description><![CDATA[
<p>I call the API directly using a custom Open WebUI plugin (pipe function) I had Flash/Sonnet write/iterate on. I have a similar pipe function for Anthropic's API but even just Sonnet is prohibitively expensive for the same performance I get with Flash for pennies.</p>
]]></description><pubDate>Sat, 10 Oct 2026 18:17:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=50035607</link><dc:creator>Primer81</dc:creator><comments>https://news.ycombinator.com/item?id=50035607</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50035607</guid></item><item><title><![CDATA[New comment by Primer81 in "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"]]></title><description><![CDATA[
<p>I've been waiting for something like this article for a month. The other AI companies are being left in the dust. I rip about 200 million tokens at least a day and spend maybe $3 with deepseek flash v4.1 for self hosted related coding tasks for ~20 projects i work on / maintain in parallel. Its a daily driver for sure. not even worth considering anything else, but maybe a locally run model on my GPU at the moment.</p>
]]></description><pubDate>Fri, 09 Oct 2026 12:43:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=50019691</link><dc:creator>Primer81</dc:creator><comments>https://news.ycombinator.com/item?id=50019691</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50019691</guid></item><item><title><![CDATA[New comment by Primer81 in "Feeling Sad about AI"]]></title><description><![CDATA[
<p>This is exactly how I feel. I can roughly understand why people feel sad, but I cannot relate. I feel more capable than ever before and am simply excited. LLMs have been a great learned tool for me especially to venture into new programming domains in my personal projects.</p>
]]></description><pubDate>Fri, 11 Sep 2026 17:39:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=49662269</link><dc:creator>Primer81</dc:creator><comments>https://news.ycombinator.com/item?id=49662269</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49662269</guid></item><item><title><![CDATA[New comment by Primer81 in "LLMs: Intelligence vs. Cost"]]></title><description><![CDATA[
<p>to choose a model, you have to consider intelligence, price, and tokens per second. would be nice to see the 3 dimensional plot.</p>
]]></description><pubDate>Wed, 02 Sep 2026 14:52:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=49537231</link><dc:creator>Primer81</dc:creator><comments>https://news.ycombinator.com/item?id=49537231</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49537231</guid></item><item><title><![CDATA[New comment by Primer81 in "A Man Who Saw Humanity from Two Billion Years Away"]]></title><description><![CDATA[
<p>Love these kinds of stories. Reminds me of the novel series "Foundation" by Isaac Asimov.</p>
]]></description><pubDate>Wed, 26 Aug 2026 17:22:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=49452715</link><dc:creator>Primer81</dc:creator><comments>https://news.ycombinator.com/item?id=49452715</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49452715</guid></item></channel></rss>