<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: moooff</title><link>https://news.ycombinator.com/user?id=moooff</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 24 Oct 2026 12:23:47 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=moooff" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by moooff in "OpenShell – A safe, private runtime for fleets of autonomous AI agents"]]></title><description><![CDATA[
<p>I was using it in an air gapped environment vs a local inference engine running a qwen-coder-next. Installtion of harnesses on the machine and other things were ruled out because of security constraints.<p>There i used it to analyze an old visual basic application which creates custom pdf files. it worked surprisingly well. it took some rounds but in the end it got all requirements and scaffolded me a skeleton for a python rewrite as a web-application. Then i worked from there with it to get a prototype.</p>
]]></description><pubDate>Thu, 22 Oct 2026 20:06:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=50200279</link><dc:creator>moooff</dc:creator><comments>https://news.ycombinator.com/item?id=50200279</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50200279</guid></item><item><title><![CDATA[New comment by moooff in "MicroLLM Lab – Try 7 tiny LLM's in the browser"]]></title><description><![CDATA[
<p>Yeah, I found a bug during model load occurring with Firefox and low VRAM machines. It is fixed now, thanks!<p>The 1060 is unusually slow. The Mac mini sounds about right. Have fun playing around and sharing. With the more VRAM of the mini you can also run Qwen 3.8 27b :)<p>I really like to showcase this to non-tech people to show what their home machines already can do WITHOUT INSTALLATION in an air-gapped scenario! And given all the recent fuss, we should not trust the big providers at all with important data.</p>
]]></description><pubDate>Tue, 29 Sep 2026 13:23:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=49892830</link><dc:creator>moooff</dc:creator><comments>https://news.ycombinator.com/item?id=49892830</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49892830</guid></item><item><title><![CDATA[New comment by moooff in "MicroLLM Lab – Try 7 tiny LLM's in the browser"]]></title><description><![CDATA[
<p>Thank you for testing. i just checked it works with Chrome.<p>FireFox seems broken in the current Version i.e. i can reproduce the bug. Working on it.<p>Which browser do you use?</p>
]]></description><pubDate>Tue, 29 Sep 2026 11:47:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=49891595</link><dc:creator>moooff</dc:creator><comments>https://news.ycombinator.com/item?id=49891595</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49891595</guid></item><item><title><![CDATA[New comment by moooff in "MicroLLM Lab – Try 7 tiny LLM's in the browser"]]></title><description><![CDATA[
<p>I did a WebGPU-based HTML Single-File Chat Application even for larger models. It just depends on your machine. It is cool to show people what can be done on their machines without installing anything. It also works in air-gapped environments.<p><a href="https://github.com/moooff/HermitUI" rel="nofollow">https://github.com/moooff/HermitUI</a></p>
]]></description><pubDate>Tue, 29 Sep 2026 06:21:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=49888978</link><dc:creator>moooff</dc:creator><comments>https://news.ycombinator.com/item?id=49888978</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49888978</guid></item><item><title><![CDATA[New comment by moooff in "Ask HN: Strategies to land fully remote $250k+ job"]]></title><description><![CDATA[
<p>This is very hard in Germany or not possible at all (beside maybe FAANG).<p>I have a PhD in Machine Learning (including Papers at SIGKDD / ECML / ACL etc.) as well as relevant working experiences and it is just not possible to get this numbers. I tried really hard to get something that pays this well (beside FAANG) that hire here because i can not move (family stuff).<p>I once talked with Google and Amazon Research (before Covid) and they told me no remote only (thats why i skipped them for now). Did this policy changed?</p>
]]></description><pubDate>Sun, 19 Dec 2021 17:17:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=29615837</link><dc:creator>moooff</dc:creator><comments>https://news.ycombinator.com/item?id=29615837</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=29615837</guid></item><item><title><![CDATA[New comment by moooff in "Ask HN: Software Engineer hitting 40: what's next?"]]></title><description><![CDATA[
<p>I am in similar position. I recently turned 40 and I’m a Development Manager but the role is moving me away from all the technical stuff I really like. I work in a classical industry position so no interesting FAANG Stuff only boring (but important) business software to keep up and running with my team.<p>The problem is that i originally did a PhD in Computer Science (Machine Learning / NLP) in 2010 and had papers at SIGKDD, ECML etc.  So this business software thing is terrible boring for me but in Germany it was reallly hard to find interesting - well paying positions - at that time in this field.<p>And now i have no idea what to do next, because i fear that all my experience as a  “Development Manager“  will not be accounted for if I apply somewhere in a more deep technical role like FAANG.</p>
]]></description><pubDate>Sat, 27 Nov 2021 21:03:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=29363449</link><dc:creator>moooff</dc:creator><comments>https://news.ycombinator.com/item?id=29363449</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=29363449</guid></item></channel></rss>