<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: codingbear</title><link>https://news.ycombinator.com/user?id=codingbear</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 17 Apr 2026 04:39:19 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=codingbear" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by codingbear in "Qwen3.5: Towards Native Multimodal Agents"]]></title><description><![CDATA[
<p>Do they mention the hardware used for training? Last I heard there was a push to use Chinese silicon. No idea how ready it is for use</p>
]]></description><pubDate>Mon, 16 Feb 2026 18:45:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=47038600</link><dc:creator>codingbear</dc:creator><comments>https://news.ycombinator.com/item?id=47038600</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47038600</guid></item><item><title><![CDATA[New comment by codingbear in "Ask HN: Who uses open LLMs and coding assistants locally? Share setup and laptop"]]></title><description><![CDATA[
<p>how are you running qwen3 with llama-vscode? I am still using qwen-2.5-7b.<p>There is an open issue about adding support for Qwn3 which I have been monitoring, would love to use Qwen3 if possible. Issue - <a href="https://github.com/ggml-org/llama.vscode/issues/55" rel="nofollow">https://github.com/ggml-org/llama.vscode/issues/55</a></p>
]]></description><pubDate>Fri, 31 Oct 2025 19:27:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=45775753</link><dc:creator>codingbear</dc:creator><comments>https://news.ycombinator.com/item?id=45775753</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45775753</guid></item><item><title><![CDATA[New comment by codingbear in "Ask HN: Who uses open LLMs and coding assistants locally? Share setup and laptop"]]></title><description><![CDATA[
<p>I use local for code completions only. Which means models supporting FIM tokens.<p>My current setup is the llama-vscode plugin + llama-server running Qwen/Qwen2.5-Coder-7B-Instruct. It leads to very fast completions, and don't have to worry about internet outages which take me out of the zone.<p>I do wish qwen-3 released a 7B model supporting FIM tokens. 7B seems to be the sweet spot for fast and usable completions</p>
]]></description><pubDate>Fri, 31 Oct 2025 19:22:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=45775708</link><dc:creator>codingbear</dc:creator><comments>https://news.ycombinator.com/item?id=45775708</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45775708</guid></item><item><title><![CDATA[New comment by codingbear in "Lua for Elixir"]]></title><description><![CDATA[
<p>what is the Lua equivalent for JVM ecosystem? An embeddable language which you allows for running user scripts in a sandbox?</p>
]]></description><pubDate>Thu, 15 May 2025 16:41:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=43996779</link><dc:creator>codingbear</dc:creator><comments>https://news.ycombinator.com/item?id=43996779</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43996779</guid></item><item><title><![CDATA[New comment by codingbear in "Ask HN: Which are the best resources to learn software architecture?"]]></title><description><![CDATA[
<p>It depends on what you mean by Software Architecture. I normally see 3 interpretations of it.<p>For some people, S/W arch is writing readable, maintainable code. Things like Design patterns, FP, TDD, microservices etc. There is a lot of literature on this out there.<p>For others, it means having the ability to design the next Kafka/Spark/React. You can get basic theory for this by reading books on Domain Modelling, Distributed computing and Algorithms. So books like The Algorithm design manual, Designing Data intensive Applications, The Parallel and Concurrent Programming in Haskell, Functional and reactive domain modelling etc. The <a href="http://aosabook.org" rel="nofollow">http://aosabook.org</a> has good case studies to read as well. However, to actually build these systems require facing the problem in the 1st place and being unable to use existing systems to solve it. Or doing phd in them. It happens rarely.<p>Finally, the last one is my day job. Which is to convert ramblings and fantasies of leadership into a production systems, minimizing the number of curse words people use when working on it. I haven't really found any good guides to do this though. Things which help me are:<p>- Always thinking what could go wrong. And if it does, who should be notified if the system can't recover. A lot of times when I don't have the answer, I ask around. Things like slack channels, mailing lists, or even having coffee with people in industry who have tackled stuff like this.<p>- Communication skills. This doesn't mean small talk, but being able to have conversations and meetings which help define requirements and ensure everyone is on the same page. Also making sure there are hard numbers. ie. instead of "fast","responsive" etc, get latency, throughput, uptime numbers.<p>- Understanding business/technical capabilities and limitations. Things like business impact(LTR etc), capabilities of current infrastructure, skill levels of various people/contractors involved etc</p>
]]></description><pubDate>Fri, 31 Jan 2020 23:02:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=22206851</link><dc:creator>codingbear</dc:creator><comments>https://news.ycombinator.com/item?id=22206851</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=22206851</guid></item><item><title><![CDATA[New comment by codingbear in "I’m Peter Roberts, immigration attorney who does work for YC and startups. AMA"]]></title><description><![CDATA[
<p>I have the same question as well.</p>
]]></description><pubDate>Fri, 25 Aug 2017 16:41:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=15099884</link><dc:creator>codingbear</dc:creator><comments>https://news.ycombinator.com/item?id=15099884</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=15099884</guid></item><item><title><![CDATA[New comment by codingbear in "An Intro to Compilers"]]></title><description><![CDATA[
<p>Can anyone help me understand what kind of employment are available in the market which requires deep knowledge of compilers?<p>I love this subject, but I don't know to which domains it is applied on outside of compiling languages like Javascript/JAVA/D/C/Rust and so on on into Machine code.</p>
]]></description><pubDate>Mon, 14 Aug 2017 15:46:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=15009495</link><dc:creator>codingbear</dc:creator><comments>https://news.ycombinator.com/item?id=15009495</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=15009495</guid></item><item><title><![CDATA[New comment by codingbear in "Ask HN: How to promote engineering culture in a company?"]]></title><description><![CDATA[
<p>How is it organised? Is there a call for presentations a day before?<p>It is a Cool Idea. Thanks for suggesting it.</p>
]]></description><pubDate>Sun, 05 Feb 2017 06:46:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=13571277</link><dc:creator>codingbear</dc:creator><comments>https://news.ycombinator.com/item?id=13571277</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=13571277</guid></item><item><title><![CDATA[Ask HN: How to promote engineering culture in a company?]]></title><description><![CDATA[
<p>The company I work in has different departments like Mobile app dev, core engineering, data analysis, depts for different products and so on. There is generally a lot of cross collaboration at the management level but nothing at the engineering level. Engineering seems to work in Silos. Anyways, I felt the company should do something about it which, with blessing of the CTO, resulted in a Hackathon. The Hackathon was a great success and now the CTO wants to discuss more ways to improve collaboration among engineers.<p>So now, I want to ask HN, what has helped to promote engineering culture in your company? Are there other things you do except Hackathons? Also, for Hackathons, what frequency do you think is the best? Weekly? Monthly? Quarterly?</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=13570936">https://news.ycombinator.com/item?id=13570936</a></p>
<p>Points: 2</p>
<p># Comments: 2</p>
]]></description><pubDate>Sun, 05 Feb 2017 04:54:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=13570936</link><dc:creator>codingbear</dc:creator><comments>https://news.ycombinator.com/item?id=13570936</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=13570936</guid></item></channel></rss>