<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: linzhangrun</title><link>https://news.ycombinator.com/user?id=linzhangrun</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 13 Jun 2026 10:46:42 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=linzhangrun" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Ask HN: What coding agents are you using?]]></title><description><![CDATA[
<p>My main coding agents are CodeX-CLI and OpenCode (Harness seems to have some problems). I also use CodeWhale, Antigravity-CLI and OpenClaude as supplements (because of network issues, I don't really dare to use Claude Code). In some special cases, bashagt.<p>What coding agents are everyone using, or do you have any recommendations? New tools are coming out like waves now.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48485669">https://news.ycombinator.com/item?id=48485669</a></p>
<p>Points: 8</p>
<p># Comments: 14</p>
]]></description><pubDate>Thu, 11 Jun 2026 02:44:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=48485669</link><dc:creator>linzhangrun</dc:creator><comments>https://news.ycombinator.com/item?id=48485669</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48485669</guid></item><item><title><![CDATA[New comment by linzhangrun in "MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second"]]></title><description><![CDATA[
<p>Maybe it is very suitable for some scenarios like autonomous driving, where reaction speed matters a lot, if they can find a way to put the hardware into a car at an acceptable cost. Maybe this is not impossible, because the hardware cost of current high-end assisted driving is already quite high?<p>At present, intelligent driving still feels, in general, like a beginner driver who drives mainly by reaction. FSD is a little better. But it still lacks the kind of “spirit” human drivers have. How to say it: when a human driver sees the car in front shaking left and right, he can guess that the driver may not be fully conscious, and then keep away from it. Current assisted driving systems are still quite weak in this kind of understanding of the world.<p>The most important thing in driving is prediction. But driving itself does not need very deep or very complicated reasoning. Recently I tried using Mimo for development, and I believe the understanding ability it can provide is absolutely more than enough for driving scenarios. Sadly, the Pro version does not have multimodal ability. And this US version seems to be trying to solve the biggest problem of using LLMs in control systems: latency.<p>Xiaomi’s car is good, but its assisted driving level is near the bottom in the same class. Compared with new EV makers, its route is quite “traditional”, just like comparing lap times with Porsche at the Nürburgring. Xiaomi’s large model team may change this.</p>
]]></description><pubDate>Thu, 11 Jun 2026 02:32:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=48485578</link><dc:creator>linzhangrun</dc:creator><comments>https://news.ycombinator.com/item?id=48485578</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48485578</guid></item><item><title><![CDATA[New comment by linzhangrun in "Anthropic's model naming, extrapolated"]]></title><description><![CDATA[
<p>Semantic inflation.</p>
]]></description><pubDate>Thu, 11 Jun 2026 02:16:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=48485488</link><dc:creator>linzhangrun</dc:creator><comments>https://news.ycombinator.com/item?id=48485488</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48485488</guid></item><item><title><![CDATA[Show HN: Get v2.0]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/Water-Run/get/releases/tag/v2.0">https://github.com/Water-Run/get/releases/tag/v2.0</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48431388">https://news.ycombinator.com/item?id=48431388</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 07 Jun 2026 03:06:07 +0000</pubDate><link>https://github.com/Water-Run/get/releases/tag/v2.0</link><dc:creator>linzhangrun</dc:creator><comments>https://news.ycombinator.com/item?id=48431388</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48431388</guid></item><item><title><![CDATA[New comment by linzhangrun in "Ask HN: What was your "oh shit" moment with GenAI?"]]></title><description><![CDATA[
<p>Lenovo's Fn+Q does not work on Fedora. Gemini resolved this by fixing the Lenovo driver code, recompiling, and deploying it.</p>
]]></description><pubDate>Sat, 06 Jun 2026 09:45:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=48423175</link><dc:creator>linzhangrun</dc:creator><comments>https://news.ycombinator.com/item?id=48423175</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48423175</guid></item><item><title><![CDATA[New comment by linzhangrun in "Xiaomi MiMo-v2.5 Series API Permanent Price Reduction Up to 99%"]]></title><description><![CDATA[
<p>Absolutely not, OpenAI is not an organization they can "control."</p>
]]></description><pubDate>Fri, 29 May 2026 01:17:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=48317790</link><dc:creator>linzhangrun</dc:creator><comments>https://news.ycombinator.com/item?id=48317790</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48317790</guid></item><item><title><![CDATA[New comment by linzhangrun in "Xiaomi MiMo-v2.5 Series API Permanent Price Reduction Up to 99%"]]></title><description><![CDATA[
<p>Yes, use VPN; they are the main clients</p>
]]></description><pubDate>Wed, 27 May 2026 02:42:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=48288876</link><dc:creator>linzhangrun</dc:creator><comments>https://news.ycombinator.com/item?id=48288876</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48288876</guid></item><item><title><![CDATA[New comment by linzhangrun in "DeepSeek makes the V4 Pro price discount permanent"]]></title><description><![CDATA[
<p>there already is a open-sourced deepseek-tui coding agent.
besides, you can always connect to opencode.</p>
]]></description><pubDate>Sat, 23 May 2026 03:40:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=48244419</link><dc:creator>linzhangrun</dc:creator><comments>https://news.ycombinator.com/item?id=48244419</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48244419</guid></item><item><title><![CDATA[New comment by linzhangrun in "DeepSeek V4 – almost on the frontier"]]></title><description><![CDATA[
<p>Strangely, my experience using DeepSeek V4 Pro on OpenCode has been absolutely awful. I switched back to GPT-5.3-CodeX as the execution model.</p>
]]></description><pubDate>Sun, 03 May 2026 09:36:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=47995196</link><dc:creator>linzhangrun</dc:creator><comments>https://news.ycombinator.com/item?id=47995196</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47995196</guid></item><item><title><![CDATA[Fedora 44]]></title><description><![CDATA[
<p>Article URL: <a href="https://fedoraproject.org/">https://fedoraproject.org/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47942734">https://news.ycombinator.com/item?id=47942734</a></p>
<p>Points: 5</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 29 Apr 2026 00:32:27 +0000</pubDate><link>https://fedoraproject.org/</link><dc:creator>linzhangrun</dc:creator><comments>https://news.ycombinator.com/item?id=47942734</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47942734</guid></item><item><title><![CDATA[Show HN: Get – get anything from your computer]]></title><description><![CDATA[
<p>Hey everyone! I recently wrote a small binary tool that calls an LLM to execute commands, designed to get various information on your computer (for when you're too lazy to remember the commands :-/)
e.g.
get "system info"
get "device ip address"
get "README.md in ~/Coding"
get "Latest version of get in <a href="https://github.com/Water-Run/get/releases/tag/v1.0" rel="nofollow">https://github.com/Water-Run/get/releases/tag/v1.0</a>"
...
It also implements simple caching and other mechanisms. Please check the GitHub homepage for detailed usage. Hope it helps everyone! :)</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47906293">https://news.ycombinator.com/item?id=47906293</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 26 Apr 2026 00:58:21 +0000</pubDate><link>https://github.com/Water-Run/get</link><dc:creator>linzhangrun</dc:creator><comments>https://news.ycombinator.com/item?id=47906293</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47906293</guid></item></channel></rss>