<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: kol3x</title><link>https://news.ycombinator.com/user?id=kol3x</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 03 Sep 2026 09:41:54 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=kol3x" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by kol3x in "Ask HN: Who wants to be hired? (September 2026)"]]></title><description><![CDATA[
<p>Location: Tbilisi, Georgia<p>Remote: Yes<p>Willing to relocate: Yes<p>Technologies: JavaScript, TypeScript, Cloudflare Workers, LLM integration, React.<p>Resume/CV: kol3x.com<p>Е-mаil: hn-september at kol3x dot com<p>I started as a fullstack JS engineer and grew into product development at my last company. I owned the ingestion layer - collecting 100k relevant messages/month from 4 platforms through a dirt-cheap serverless back-end on Cloudflare Workers.<p>We worked with LLMs deeply, especially in code generation research. I was part of a small team developing SpecGEM, a fine-tuned model that generates Cloudflare Workers code from JSDoc comments and is designed to outperform mainstream LLMs at this narrow task. <a href="https://dn.institute/research/ai/specgem/" rel="nofollow">https://dn.institute/research/ai/specgem/</a><p>Last month I released a self-hosted LLM assistant on Cloudflare Workers that predictably compounds context across conversations. <a href="https://github.com/kol3x/pawmc" rel="nofollow">https://github.com/kol3x/pawmc</a><p>Looking for a remote role where I can own work end-to-end. Stack-wise I'm strongest on Cloudflare Workers, JavaScript/TypeScript, practical LLM integration, React.<p>CV, LinkedIn, and GitHub are also linked at <a href="https://kol3x.com" rel="nofollow">https://kol3x.com</a></p>
]]></description><pubDate>Tue, 01 Sep 2026 15:01:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=49522899</link><dc:creator>kol3x</dc:creator><comments>https://news.ycombinator.com/item?id=49522899</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49522899</guid></item><item><title><![CDATA[Show HN: Simple self-hosted LLM assistant with user-steered compounding context]]></title><description><![CDATA[
<p>I built a personal LLM assistant on Cloudflare Workers + Durable Objects. You specify a category and topic when starting a new conversation, so the backend maintains a summary for each category/topic - building up as more conversations happen under the same one.<p>There is no complicated RAG, embeddings, or agentic magic, but the category/topic summaries system just works, and I've genuinely found it super handy and have been using it daily for my life and work.<p>I started it to get familiar with Durable Objects and to test out this idea draft I had buried on my board. After recently losing my job, I started working on it more. Testing it with my friends and focusing on it being as straightforward as possible to understand, deploy and use. This week I open-sourced it for more people to try<p>Repo: <a href="https://github.com/kol3x/pawmc" rel="nofollow">https://github.com/kol3x/pawmc</a><p>Some details:<p>- $0 cost on Cloudflare's free tier with default configuration
- Everything in a singleton Durable Object
- Workers AI as the default provider
- OpenRouter support for more stable access and bigger models (there, you'd need to pay for tokens)</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49169771">https://news.ycombinator.com/item?id=49169771</a></p>
<p>Points: 5</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 04 Aug 2026 14:48:35 +0000</pubDate><link>https://github.com/kol3x/pawmc</link><dc:creator>kol3x</dc:creator><comments>https://news.ycombinator.com/item?id=49169771</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49169771</guid></item><item><title><![CDATA[New comment by kol3x in "Cloudflare: The Agent Readiness score. Is your site agent-ready?"]]></title><description><![CDATA[
<p>You already now some companies will optimize for this score but in the opposite way...</p>
]]></description><pubDate>Fri, 17 Apr 2026 13:39:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=47805841</link><dc:creator>kol3x</dc:creator><comments>https://news.ycombinator.com/item?id=47805841</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47805841</guid></item><item><title><![CDATA[Cloudflare: The Agent Readiness score. Is your site agent-ready?]]></title><description><![CDATA[
<p>Article URL: <a href="https://blog.cloudflare.com/agent-readiness/">https://blog.cloudflare.com/agent-readiness/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47805833">https://news.ycombinator.com/item?id=47805833</a></p>
<p>Points: 6</p>
<p># Comments: 4</p>
]]></description><pubDate>Fri, 17 Apr 2026 13:38:24 +0000</pubDate><link>https://blog.cloudflare.com/agent-readiness/</link><dc:creator>kol3x</dc:creator><comments>https://news.ycombinator.com/item?id=47805833</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47805833</guid></item><item><title><![CDATA[New comment by kol3x in "Cloudflare's AI Platform: an inference layer designed for agents"]]></title><description><![CDATA[
<p>Would be nice to filter out "proxied" models in the Workers AI page.</p>
]]></description><pubDate>Fri, 17 Apr 2026 13:28:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=47805716</link><dc:creator>kol3x</dc:creator><comments>https://news.ycombinator.com/item?id=47805716</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47805716</guid></item><item><title><![CDATA[New comment by kol3x in "Ask HN: Who is hiring? (November 2025)"]]></title><description><![CDATA[
<p>DN Institute | Software Engineer | Full Remote (World)<p>Distributed Networks Institute’s mission is to achieve sustainable technological growth and resilience by leveraging scientific, engineering, and organizational principles of distributed networks. We are a part of a 501(c)3 non-profit incubator in Washington DC called BlockShop.<p>We just released a paid Software Development challenge with a monetary bounty and a chance to become part of our team. It involves improving a Telegram Connector, deployed on Cloudflare Workers (JS + Python). You can find the full description and more information about challenge program in the Github issue here: <a href="https://github.com/1712n/dn-institute/issues/491" rel="nofollow">https://github.com/1712n/dn-institute/issues/491</a></p>
]]></description><pubDate>Mon, 03 Nov 2025 16:01:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=45800486</link><dc:creator>kol3x</dc:creator><comments>https://news.ycombinator.com/item?id=45800486</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45800486</guid></item></channel></rss>