<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: theapadayo</title><link>https://news.ycombinator.com/user?id=theapadayo</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 29 Apr 2026 16:06:12 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=theapadayo" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by theapadayo in "Ghostty is leaving GitHub"]]></title><description><![CDATA[
<p>> TFS (what microsoft had/pushed before acquiring github)<p>It's still around. It's just called Azure DevOps now. I personally think it's great for what it does.</p>
]]></description><pubDate>Wed, 29 Apr 2026 00:53:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=47942885</link><dc:creator>theapadayo</dc:creator><comments>https://news.ycombinator.com/item?id=47942885</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47942885</guid></item><item><title><![CDATA[New comment by theapadayo in "Offline Reinforcement Learning for LLM Multi-Step Reasoning"]]></title><description><![CDATA[
<p>Well I guess we finally got the mythical 'Q*'. Or at least some variant of it using energy functions (I think that's what they mean by 'soft' Q-learning?). The extra boost from using the value function at test time is interesting as well.</p>
]]></description><pubDate>Mon, 23 Dec 2024 13:52:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=42494368</link><dc:creator>theapadayo</dc:creator><comments>https://news.ycombinator.com/item?id=42494368</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42494368</guid></item></channel></rss>