<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: sergeyk</title><link>https://news.ycombinator.com/user?id=sergeyk</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 06 Sep 2026 08:28:31 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=sergeyk" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Why coding agents belong in remote sandboxes]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.superconductor.com/blog/remote-sandboxes-agent-security">https://www.superconductor.com/blog/remote-sandboxes-agent-security</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49172611">https://news.ycombinator.com/item?id=49172611</a></p>
<p>Points: 14</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 04 Aug 2026 18:12:30 +0000</pubDate><link>https://www.superconductor.com/blog/remote-sandboxes-agent-security</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=49172611</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49172611</guid></item><item><title><![CDATA[New comment by sergeyk in "Launch HN: Hoplite (YC S26) – Effortlessly deploy cloud coding agents"]]></title><description><![CDATA[
<p>Check out <a href="https://superconductor.com" rel="nofollow">https://superconductor.com</a>: supports docker and env setup is done for you by an agent when you connect repo</p>
]]></description><pubDate>Tue, 04 Aug 2026 16:01:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=49170777</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=49170777</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49170777</guid></item><item><title><![CDATA[New comment by sergeyk in "The Code-Only Agent"]]></title><description><![CDATA[
<p>What's crazy is that this has been possible since before ChatGPT: <a href="https://x.com/sergeykarayev/status/1569377881440276481" rel="nofollow">https://x.com/sergeykarayev/status/1569377881440276481</a></p>
]]></description><pubDate>Mon, 19 Jan 2026 19:11:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=46683118</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=46683118</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46683118</guid></item><item><title><![CDATA[New comment by sergeyk in "Claude Code On-the-Go"]]></title><description><![CDATA[
<p>Check out superconductor.dev (I’m building it), if you want live app previews, docker-in-docker functionality, multiple agents in one mobile app, and more.</p>
]]></description><pubDate>Sun, 04 Jan 2026 21:56:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=46492700</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=46492700</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46492700</guid></item><item><title><![CDATA[New comment by sergeyk in "Ask HN: How are you LLM-coding in an established code base?"]]></title><description><![CDATA[
<p>Our foundational design value was compute instance startup speed. We've made some design decisions and evaluated several "neocloud" providers with this goal in mind.<p>Currently, from launching an agent to that agent being able to run tests in our Rails docker-compose environment (and to the live app preview running), is about 30 seconds. If that agent finishes their work and goes to sleep, and then hours later you come back to send a message, it'll wake up in about the same time.<p>(And, of course, you can launch many agents at once -- they're all going to be ready at roughly the same time.)</p>
]]></description><pubDate>Sat, 20 Dec 2025 00:39:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=46332670</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=46332670</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46332670</guid></item><item><title><![CDATA[New comment by sergeyk in "Ask HN: How are you LLM-coding in an established code base?"]]></title><description><![CDATA[
<p>> AFAICT, there’s no service that lets me: give a prompt, write the code, spin up all this infra, run Playwright, handle database migrations, and let me manually poke at the system. We approximate this with GitHub Actions, but that doesn’t help with manual verification or DB work.<p>I think this is almost exactly what we've built with <a href="https://superconductor.dev" rel="nofollow">https://superconductor.dev</a><p>- set up a project with one or more repos<p>- set up your environment any way you want, including using docker containers<p>- run any number of Claude Code, Codex, Gemini, Amp, or OpenCode agents on a prompt, or "ticket" (we can add Cursor CLI also)<p>- each ticket implementation has a fully running "app preview", which you can use just like you use your locally running setup. your running web app is even shown in a pane right next to chat and diff<p>- chat with the agent inside of a ticket implementation, and when you're happy, submit to github<p>(agents can even take screenshots)<p>happy to onboard you if that sounds interesting, just ping me at sergey@superconductor.dev</p>
]]></description><pubDate>Fri, 19 Dec 2025 21:29:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=46331170</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=46331170</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46331170</guid></item><item><title><![CDATA[New comment by sergeyk in "Jules, our asynchronous coding agent"]]></title><description><![CDATA[
<p>This is exactly why we built superconductor.dev, which has live app preview for each agent. We support Claude Code as well as Gemini, Codex, Amp. If you want to check it out just mention HN in your signup form and I’ll prioritize you :)</p>
]]></description><pubDate>Wed, 06 Aug 2025 23:20:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=44818977</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=44818977</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44818977</guid></item><item><title><![CDATA[New comment by sergeyk in "Launch HN: Skyvern (YC S23) – open-source AI agent for browser automations"]]></title><description><![CDATA[
<p>Congrats! Do you have numbers on WebArena (<a href="https://webarena.dev" rel="nofollow">https://webarena.dev</a>) or VisualWebArena (<a href="https://jykoh.com/vwa" rel="nofollow">https://jykoh.com/vwa</a>)?</p>
]]></description><pubDate>Thu, 24 Oct 2024 18:44:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=41938369</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=41938369</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41938369</guid></item><item><title><![CDATA[Lecture Videos from LLM Bootcamp]]></title><description><![CDATA[
<p>Article URL: <a href="https://fullstackdeeplearning.com/llm-bootcamp/">https://fullstackdeeplearning.com/llm-bootcamp/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=35908542">https://news.ycombinator.com/item?id=35908542</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 11 May 2023 21:22:03 +0000</pubDate><link>https://fullstackdeeplearning.com/llm-bootcamp/</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=35908542</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35908542</guid></item><item><title><![CDATA[New comment by sergeyk in "AI language models are struggling to “get” math"]]></title><description><![CDATA[
<p>Live demo of this you can run: <a href="https://twitter.com/sergeykarayev/status/1569377881440276481" rel="nofollow">https://twitter.com/sergeykarayev/status/1569377881440276481</a></p>
]]></description><pubDate>Thu, 13 Oct 2022 02:05:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=33186305</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=33186305</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33186305</guid></item><item><title><![CDATA[The Art of Production: Rrose (Techno, Player Piano)]]></title><description><![CDATA[
<p>Article URL: <a href="https://ra.co/features/3619">https://ra.co/features/3619</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=28010190">https://news.ycombinator.com/item?id=28010190</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 30 Jul 2021 17:21:12 +0000</pubDate><link>https://ra.co/features/3619</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=28010190</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=28010190</guid></item><item><title><![CDATA[Data Management for Full Stack Deep Learning]]></title><description><![CDATA[
<p>Article URL: <a href="https://course.fullstackdeeplearning.com/course-content/data-management">https://course.fullstackdeeplearning.com/course-content/data-management</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=23909086">https://news.ycombinator.com/item?id=23909086</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 21 Jul 2020 17:52:33 +0000</pubDate><link>https://course.fullstackdeeplearning.com/course-content/data-management</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=23909086</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=23909086</guid></item><item><title><![CDATA[New comment by sergeyk in "Ask HN: Solo devs, how do you plan your development?"]]></title><description><![CDATA[
<p>> (I've yet to find a technological solution that doesn't make it way too easy to accumulate clutter.)<p>Try NotePlan (<a href="https://noteplan.co" rel="nofollow">https://noteplan.co</a>)</p>
]]></description><pubDate>Mon, 30 Dec 2019 20:02:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=21916175</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=21916175</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=21916175</guid></item><item><title><![CDATA[Infrastructure Landscape for Full Stack Deep Learning [video]]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.youtube.com/watch?v=a33nwW4-rn8">https://www.youtube.com/watch?v=a33nwW4-rn8</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=20186024">https://news.ycombinator.com/item?id=20186024</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 14 Jun 2019 19:36:23 +0000</pubDate><link>https://www.youtube.com/watch?v=a33nwW4-rn8</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=20186024</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=20186024</guid></item><item><title><![CDATA[Videos from Full Stack Deep Learning Program [March 2019]]]></title><description><![CDATA[
<p>Article URL: <a href="https://fullstackdeeplearning.com/march2019">https://fullstackdeeplearning.com/march2019</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=19675849">https://news.ycombinator.com/item?id=19675849</a></p>
<p>Points: 16</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 16 Apr 2019 18:05:28 +0000</pubDate><link>https://fullstackdeeplearning.com/march2019</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=19675849</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=19675849</guid></item><item><title><![CDATA[Troubleshooting Deep Neural Networks: A Field Guide to Fixing Your Model]]></title><description><![CDATA[
<p>Article URL: <a href="http://josh-tobin.com/troubleshooting-deep-neural-networks">http://josh-tobin.com/troubleshooting-deep-neural-networks</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=19106484">https://news.ycombinator.com/item?id=19106484</a></p>
<p>Points: 18</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 07 Feb 2019 17:00:23 +0000</pubDate><link>http://josh-tobin.com/troubleshooting-deep-neural-networks</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=19106484</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=19106484</guid></item><item><title><![CDATA[Troubleshooting Deep Neural Networks: a decision tree for debugging your model]]></title><description><![CDATA[
<p>Article URL: <a href="https://twitter.com/josh_tobin_/status/1088830262794833921">https://twitter.com/josh_tobin_/status/1088830262794833921</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=19026128">https://news.ycombinator.com/item?id=19026128</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 29 Jan 2019 13:38:56 +0000</pubDate><link>https://twitter.com/josh_tobin_/status/1088830262794833921</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=19026128</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=19026128</guid></item><item><title><![CDATA[New comment by sergeyk in "The Prado Museum, Spain’s Cultural Jewel, Turns 200"]]></title><description><![CDATA[
<p>If you find yourself in Madrid, you will not regret making time for the Prado. Whereas some museums, like the Hermitage, go for quantity, the Prado seems to pride itself on extreme curation. It did not feel like a huge museum (at least the tour of it that I did), but every single room had at least one true masterpiece.</p>
]]></description><pubDate>Mon, 28 Jan 2019 23:42:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=19022258</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=19022258</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=19022258</guid></item><item><title><![CDATA[Where have all the workers gone? – New Yorker]]></title><description><![CDATA[
<p>Article URL: <a href="http://m.newyorker.com/online/blogs/comment/2014/02/where-have-all-the-workers-gone.html">http://m.newyorker.com/online/blogs/comment/2014/02/where-have-all-the-workers-gone.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=7516911">https://news.ycombinator.com/item?id=7516911</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 02 Apr 2014 16:52:10 +0000</pubDate><link>http://m.newyorker.com/online/blogs/comment/2014/02/where-have-all-the-workers-gone.html</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=7516911</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=7516911</guid></item><item><title><![CDATA[New comment by sergeyk in "Why Privacy Matters Even if You Have 'Nothing to Hide'"]]></title><description><![CDATA[
<p>"If I have nothing to hide, you've got no reason to look."</p>
]]></description><pubDate>Wed, 13 Jun 2012 17:32:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=4107200</link><dc:creator>sergeyk</dc:creator><comments>https://news.ycombinator.com/item?id=4107200</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=4107200</guid></item></channel></rss>