<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: Gakho</title><link>https://news.ycombinator.com/user?id=Gakho</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 23 Apr 2026 05:59:52 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=Gakho" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by Gakho in "Show HN: An open-source Operator that can use computers"]]></title><description><![CDATA[
<p>what's the most interesting use case you've seen so far?</p>
]]></description><pubDate>Tue, 08 Apr 2025 15:00:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=43622572</link><dc:creator>Gakho</dc:creator><comments>https://news.ycombinator.com/item?id=43622572</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43622572</guid></item><item><title><![CDATA[New comment by Gakho in "Show HN: Mastra – Open-source JS agent framework, by the developers of Gatsby"]]></title><description><![CDATA[
<p>I'm wondering since there seem to be a lot of frameworks/websites that support evals, even OpenAI has evals.<p>Do you think that a lot of these components like observability and evals will eventually be consumed by either providers (like OpenAI) or an orchestration framework like Mastra (when using multiple providers, though even if you're using just one provider for many tasks I can see it belonging to the orchestration framework)?</p>
]]></description><pubDate>Wed, 19 Feb 2025 18:10:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=43105291</link><dc:creator>Gakho</dc:creator><comments>https://news.ycombinator.com/item?id=43105291</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43105291</guid></item><item><title><![CDATA[New comment by Gakho in "Show HN: Mastra – Open-source JS agent framework, by the developers of Gatsby"]]></title><description><![CDATA[
<p>Congrats on launching. I've noticed that switching prompts without edits between different LLM providers has degradation on performance. I'm wondering if you guys have noticed how developers do these "translations", I'm wondering since maybe your eval framework might have data for best practices.</p>
]]></description><pubDate>Wed, 19 Feb 2025 17:56:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=43105129</link><dc:creator>Gakho</dc:creator><comments>https://news.ycombinator.com/item?id=43105129</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43105129</guid></item><item><title><![CDATA[Ask HN: Good books on robotics]]></title><description><![CDATA[
<p>Hi,<p>I'm starting to get interested in robotics and I was wondering if you guys could recommend any good books in the field. It's fine if the books only cover a subsection like vision, actuators or sensors. I just want to understand more about the field. Thanks</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=8191504">https://news.ycombinator.com/item?id=8191504</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 18 Aug 2014 05:13:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=8191504</link><dc:creator>Gakho</dc:creator><comments>https://news.ycombinator.com/item?id=8191504</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=8191504</guid></item></channel></rss>