<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: olaird25</title><link>https://news.ycombinator.com/user?id=olaird25</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 13 Sep 2026 07:47:28 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=olaird25" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by olaird25 in "We must pace the frontier"]]></title><description><![CDATA[
<p>Vitalik Buterin: “...But currently, I see zero plans for how to deal with an ASI transition that are not naive. Perhaps humanity is stuck with a choice between naive and naive squared (or maybe even naive squared and naive cubed), so I feel inclined to cut some slack to people who are trying.”</p>
]]></description><pubDate>Sat, 12 Sep 2026 15:33:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=49673376</link><dc:creator>olaird25</dc:creator><comments>https://news.ycombinator.com/item?id=49673376</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49673376</guid></item><item><title><![CDATA[New comment by olaird25 in "Show HN: Drift – an embedding-model upgrade should be a rotation, not a reindex"]]></title><description><![CDATA[
<p>Interesting. But if you are upgrading your embedding model, wouldn't you want to re-embed to get its benefits on old entries?</p>
]]></description><pubDate>Wed, 10 Jun 2026 17:03:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=48479302</link><dc:creator>olaird25</dc:creator><comments>https://news.ycombinator.com/item?id=48479302</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48479302</guid></item><item><title><![CDATA[New comment by olaird25 in "Show HN: RainBreak App – The AI doesn't need a break. But you do"]]></title><description><![CDATA[
<p>Very nice! How did you implement your rain effect?</p>
]]></description><pubDate>Tue, 09 Jun 2026 22:30:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=48468703</link><dc:creator>olaird25</dc:creator><comments>https://news.ycombinator.com/item?id=48468703</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48468703</guid></item><item><title><![CDATA[New comment by olaird25 in "Show HN: Formally verified polygon intersection – Opus 4.8 oneshots, prev failed"]]></title><description><![CDATA[
<p>Nice. So is the js/lean interface using exact rationals?</p>
]]></description><pubDate>Fri, 05 Jun 2026 14:54:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=48413360</link><dc:creator>olaird25</dc:creator><comments>https://news.ycombinator.com/item?id=48413360</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48413360</guid></item><item><title><![CDATA[New comment by olaird25 in "Show HN: Formally verified polygon intersection – Opus 4.8 oneshots, prev failed"]]></title><description><![CDATA[
<p>Is the web demo compiled from the lean?</p>
]]></description><pubDate>Thu, 04 Jun 2026 22:58:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=48405814</link><dc:creator>olaird25</dc:creator><comments>https://news.ycombinator.com/item?id=48405814</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48405814</guid></item><item><title><![CDATA[New comment by olaird25 in "Tokenization Is the Bottleneck You're Not Measuring"]]></title><description><![CDATA[
<p>Have you tried just using a faster tokenization library?<p>Github's BPE crate (<a href="https://crates.io/crates/bpe" rel="nofollow">https://crates.io/crates/bpe</a>) advertises >10x
speedup relative to HF, as do others.</p>
]]></description><pubDate>Tue, 26 May 2026 17:31:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=48282913</link><dc:creator>olaird25</dc:creator><comments>https://news.ycombinator.com/item?id=48282913</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48282913</guid></item><item><title><![CDATA[New comment by olaird25 in "AI Killed Stack Overflow (and why that sucks)"]]></title><description><![CDATA[
<p>"Writing the question WAS the lesson"
Indeed!</p>
]]></description><pubDate>Tue, 26 May 2026 16:35:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=48282080</link><dc:creator>olaird25</dc:creator><comments>https://news.ycombinator.com/item?id=48282080</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48282080</guid></item><item><title><![CDATA[New comment by olaird25 in "Code Mode: the better way to use MCP"]]></title><description><![CDATA[
<p>This seems exactly right. Its pretty common to watch your agent making the same mcp tool call again and again as it works through a list. These kinds of cases are solved by letting the agent just call any of its mcp tools in a script.</p>
]]></description><pubDate>Sat, 27 Sep 2025 22:27:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=45399882</link><dc:creator>olaird25</dc:creator><comments>https://news.ycombinator.com/item?id=45399882</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45399882</guid></item></channel></rss>