<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: Asyne</title><link>https://news.ycombinator.com/user?id=Asyne</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 29 Jul 2026 02:08:25 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=Asyne" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by Asyne in "ChatGPT Pro now starts at $100/month"]]></title><description><![CDATA[
<p>+1 to this, I've found GPT/Codex models consistently stronger in engineering tasks (such as debugging complex, cross-systems issues, concurrency problems, etc).<p>I use both OpenAI and Anthropic models, though for different purposes, what surprises me is how underrated GPT still feels (or, alternatively, how overhyped Anthropic models can be) given how capable it is in these scenarios. There also seems to be relatively little recognition of this in the broader community (like your recent YouTube video). My guess is that demand skews toward general codegen rather than the kind of deep debugging and systems work where these differences really show.</p>
]]></description><pubDate>Thu, 09 Apr 2026 18:41:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=47707836</link><dc:creator>Asyne</dc:creator><comments>https://news.ycombinator.com/item?id=47707836</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47707836</guid></item><item><title><![CDATA[Kafka 3.3: Zookeeper replacement KRaft marked as Production Ready]]></title><description><![CDATA[
<p>Article URL: <a href="https://kafka.apache.org/downloads">https://kafka.apache.org/downloads</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=33110077">https://news.ycombinator.com/item?id=33110077</a></p>
<p>Points: 6</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 06 Oct 2022 16:09:06 +0000</pubDate><link>https://kafka.apache.org/downloads</link><dc:creator>Asyne</dc:creator><comments>https://news.ycombinator.com/item?id=33110077</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33110077</guid></item><item><title><![CDATA[Headless Chrome and Cross-Platform Screenshot Capturing]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/asyne/mindless">https://github.com/asyne/mindless</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=14270321">https://news.ycombinator.com/item?id=14270321</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 05 May 2017 00:55:00 +0000</pubDate><link>https://github.com/asyne/mindless</link><dc:creator>Asyne</dc:creator><comments>https://news.ycombinator.com/item?id=14270321</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=14270321</guid></item></channel></rss>