<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: daniban</title><link>https://news.ycombinator.com/user?id=daniban</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 18 Jun 2026 07:22:08 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=daniban" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by daniban in "GLM-5.2 is the new leading open weights model on Artificial Analysis"]]></title><description><![CDATA[
<p>I'm curious what harness everyone is using for these? I want to start to test some of these open models but don't know what tools people use to get these working "agenticaly"</p>
]]></description><pubDate>Wed, 17 Jun 2026 17:21:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=48573541</link><dc:creator>daniban</dc:creator><comments>https://news.ycombinator.com/item?id=48573541</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48573541</guid></item><item><title><![CDATA[New comment by daniban in "Is Meta destroying its engineering organization?"]]></title><description><![CDATA[
<p>I think Tim Cook tried to...</p>
]]></description><pubDate>Tue, 16 Jun 2026 18:16:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=48559575</link><dc:creator>daniban</dc:creator><comments>https://news.ycombinator.com/item?id=48559575</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48559575</guid></item><item><title><![CDATA[New comment by daniban in "Running local models is good now"]]></title><description><![CDATA[
<p>With Apple silicon and now the RTX Spark there are real discussions whether local AI is the future. The only problem is Western open source models are so far behind. I genuinely feel there's a push to fix this. Gemma is getting more frequent releases and Nvdia is quietly creating very cool small models. I hope both the hardware and models catch up and local really does emerge.</p>
]]></description><pubDate>Tue, 16 Jun 2026 16:13:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=48557541</link><dc:creator>daniban</dc:creator><comments>https://news.ycombinator.com/item?id=48557541</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48557541</guid></item><item><title><![CDATA[New comment by daniban in "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"]]></title><description><![CDATA[
<p>I haven't but I'm on the path to attempt this. I want to get a DGX Spark and will be trying Qwen and Kimi.</p>
]]></description><pubDate>Tue, 16 Jun 2026 15:19:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=48556634</link><dc:creator>daniban</dc:creator><comments>https://news.ycombinator.com/item?id=48556634</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48556634</guid></item><item><title><![CDATA[New comment by daniban in "SpaceX to buy Cursor for $60B"]]></title><description><![CDATA[
<p>I'm genuinely excited for Cursor Composer 3. A Cursor model with Grok resources could compete with OpenAI and Anthropic.</p>
]]></description><pubDate>Tue, 16 Jun 2026 15:17:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=48556608</link><dc:creator>daniban</dc:creator><comments>https://news.ycombinator.com/item?id=48556608</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48556608</guid></item></channel></rss>