<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: srvraw</title><link>https://news.ycombinator.com/user?id=srvraw</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 10 Oct 2026 03:24:58 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=srvraw" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by srvraw in "Celld: Self-hosted, distributed Durable Objects"]]></title><description><![CDATA[
<p>I haven't deep-dived into celld. Does it requires s3's strong consistency to be correct? or is any s3 api compatible object storage sufficient even if they lack strong consistency guarantee?</p>
]]></description><pubDate>Thu, 06 Aug 2026 12:44:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=49195889</link><dc:creator>srvraw</dc:creator><comments>https://news.ycombinator.com/item?id=49195889</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49195889</guid></item><item><title><![CDATA[New comment by srvraw in "Beating GPT-5.6 Sol on retrieval with 100x cheaper open models"]]></title><description><![CDATA[
<p>could you share more about what you mean by "general patterns & search strategies"? I can think of it being along the lines of searching over specific tables or databases for queries in certain context. It's an exciting line of work and I'm interested because I need something like this for the problem I'm solving atm. So, I'd like to understand how the training generalizes</p>
]]></description><pubDate>Thu, 06 Aug 2026 09:00:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=49194247</link><dc:creator>srvraw</dc:creator><comments>https://news.ycombinator.com/item?id=49194247</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49194247</guid></item></channel></rss>