<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: these</title><link>https://news.ycombinator.com/user?id=these</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 06 Aug 2026 05:18:20 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=these" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by these in "Rewriting Bun in Rust"]]></title><description><![CDATA[
<p>> That’s assuming that you actually get those 50 people to work without blockers, stepping on each other, or other coordination issues. The coordination complexity alone is astounding.<p>This is a question of exceptional management, which needs to be present both in the Claude and human cases, and is scarce. Not everyone given the Claude tokens would be able to deliver the same result.</p>
]]></description><pubDate>Thu, 09 Jul 2026 03:02:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=48840463</link><dc:creator>these</dc:creator><comments>https://news.ycombinator.com/item?id=48840463</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48840463</guid></item><item><title><![CDATA[New comment by these in "Software Is Made Between Commits"]]></title><description><![CDATA[
<p>This seems like a great way to facilitate data gathering for improving LLMs coding performance.<p>If previously you needed to take action 1, 2, 3 to go from state A to B, all you saw was the change from A, B. Now you see intermediates 1, 2, 3 and can train the models to skip straight to B with the added context of the intermediate states.</p>
]]></description><pubDate>Thu, 11 Jun 2026 18:19:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=48494343</link><dc:creator>these</dc:creator><comments>https://news.ycombinator.com/item?id=48494343</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48494343</guid></item><item><title><![CDATA[New comment by these in "Accelerating Gemma 4: faster inference with multi-token prediction drafters"]]></title><description><![CDATA[
<p>Has anyone managed to get this to work in LM Studio? They've got a option in the UI, but it never seems to allow me to enable it.</p>
]]></description><pubDate>Tue, 05 May 2026 16:49:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=48025065</link><dc:creator>these</dc:creator><comments>https://news.ycombinator.com/item?id=48025065</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48025065</guid></item></channel></rss>