<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: ezulabs</title><link>https://news.ycombinator.com/user?id=ezulabs</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 23 Apr 2026 10:52:56 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=ezulabs" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by ezulabs in "Ask HN: Freelancer? Seeking freelancer? (April 2026)"]]></title><description><![CDATA[
<p>SEEKING WORK: EU, Remote Worldwide<p>Technologies: AI, CC, MLX, RL, llama.cpp, Android, Kotlin, NextJS, Embedded<p>Résumé/CV: www.ezulabs.com <a href="https://github.com/ezulabs" rel="nofollow">https://github.com/ezulabs</a>, available upon request<p>Email: contact@ezulabs.com</p>
]]></description><pubDate>Thu, 02 Apr 2026 16:46:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=47616855</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=47616855</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47616855</guid></item><item><title><![CDATA[New comment by ezulabs in "Ask HN: Who wants to be hired? (April 2026)"]]></title><description><![CDATA[
<p>Location: EU timezone, US 4 hours overlap
Remote: yes<p>Willing to relocate: yes<p>Technologies: AI, CC, MLX, RL, llama.cpp, Android, Kotlin, NextJS, Embedded<p>Résumé/CV: <a href="https://github.com/ezulabs" rel="nofollow">https://github.com/ezulabs</a>, available upon request<p>Email: contact@ezulabs.com</p>
]]></description><pubDate>Wed, 01 Apr 2026 16:37:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=47603196</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=47603196</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47603196</guid></item><item><title><![CDATA[New comment by ezulabs in "Ask HN: Who wants to be hired? (March 2026)"]]></title><description><![CDATA[
<p>Location: EU timezone, can overlap US 4 hours<p>Remote: yes<p>Willing to relocate: no<p>Technologies: AI, MLX, llama.cpp, Kotlin, NextJS, Embedded<p>Résumé/CV: <a href="https://github.com/ezulabs" rel="nofollow">https://github.com/ezulabs</a>, available upo request<p>Email: contact@ezulabs.com<p>You will be hiring an ex-silicon valley engineer for junior engineer level cost. Please no ego and bs companies.</p>
]]></description><pubDate>Mon, 02 Mar 2026 21:37:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=47224481</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=47224481</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47224481</guid></item><item><title><![CDATA[New comment by ezulabs in "Ask HN: Starting a New Role with Ada"]]></title><description><![CDATA[
<p>I would try Claude Code with an Ada LSP server. Use AI to get the high-level architecture diagrams, question the codebase. You can write a new skill with all your findings about Ada best practices. Also try CodeRabbit if it already supports Ada. Congratulations on the new job, best of luck.</p>
]]></description><pubDate>Wed, 25 Feb 2026 22:02:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=47158631</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=47158631</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47158631</guid></item><item><title><![CDATA[New comment by ezulabs in "LT6502: A 6502-based homebrew laptop"]]></title><description><![CDATA[
<p>I stop seeing those issues after starting using Bambulab X1 3d printer, it just works 99 percent of the time. My old ender 3 v2 had those issues due to bed changing its shape during printing(thin metal changing shape in micro level due to temp and mechanical stress with 4 knobs pulling down), not sticking well, not enough fast cooling or cooling effects bed temp profile, way off even with auto level probes. Also open 3d printer with bunch of air flow is a killer for those prints. OP should try Bambulab like enclosed more accurate 3d printer from a local 3d print shop or a hackerspace after locking the design and enclosure iterations.</p>
]]></description><pubDate>Mon, 16 Feb 2026 17:41:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=47037864</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=47037864</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47037864</guid></item><item><title><![CDATA[New comment by ezulabs in "OrthoRay – A native, lightweight DICOM viewer written in Rust/wgpu by a surgeon"]]></title><description><![CDATA[
<p>Can this be used for Haller index?<p>Recently my family member start to deal with Pectus excavatum, the xray provider and the doctor were not on the same platform and witnessed doctor doing manual calculation for it. I wished there was a way do it with web upload and get the result right a way that is error prone and accurate.</p>
]]></description><pubDate>Thu, 12 Feb 2026 18:28:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=46992929</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46992929</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46992929</guid></item><item><title><![CDATA[New comment by ezulabs in "Run Pebble OS in Browser via WASM"]]></title><description><![CDATA[
<p>Can already see a nice web based AI app builder on the way, also can be used to quickly try apps before pushing to the device as interactive app store.<p>Please watch out some qemu targets for Cortex m0 or m3, increasing ram from linker out of supported ranges will cause random crashes. Would love to contribute if you are looking for people to crash some issues.<p>Awesome effort btw.</p>
]]></description><pubDate>Thu, 12 Feb 2026 18:23:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=46992823</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46992823</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46992823</guid></item><item><title><![CDATA[New comment by ezulabs in "Ask HN: How to get started with robotics as a hobbyist?"]]></title><description><![CDATA[
<p>I would always prefer to start with a kit that will work right a way end to end, than focus on each problem subset to do deep dive. so101 is a highly available 3d printed and servo motor based robotic arm. That can be combined with nvidia orin like sbc as a good starting point.<p>Worth to check also <a href="https://www.printables.com/" rel="nofollow">https://www.printables.com/</a> for small cute 3d printed robot projects that you can build using stm32 or esp32 boards. You shall check Adafruit/Sparkfun like websites for dev boards, they even support micro python for quick prototypes.<p><a href="https://www.hackster.io/shahizat/running-lerobot-so-101-arm-kit-using-nvidia-jetson-agx-orin-19b8a4" rel="nofollow">https://www.hackster.io/shahizat/running-lerobot-so-101-arm-...</a></p>
]]></description><pubDate>Thu, 12 Feb 2026 18:16:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=46992712</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46992712</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46992712</guid></item><item><title><![CDATA[New comment by ezulabs in "Ask HN: What are you working on? (February 2026)"]]></title><description><![CDATA[
<p>Building an AI debugger for embedded systems.<p>You know that feeling when your microcontroller crashes and you spend 3 hours staring at cryptic registers trying to figure out why? Yeah, I got tired of that.<p>So I built an MCP server that lets Claude talk directly to GDB.
Now instead of manually decoding CFSR registers, I just ask "why did it crash?" and get back "division by zero at line 142 in calculate_average()".<p>It's pretty satisfying to watch Claude diagnose a deadlock between two RP2040 cores in 10 seconds - something that would've ruined my entire afternoon.<p>Just shipped v0.1.0: <a href="https://github.com/ezulabs/embeddedgdbmcp" rel="nofollow">https://github.com/ezulabs/embeddedgdbmcp</a></p>
]]></description><pubDate>Mon, 09 Feb 2026 15:32:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=46946324</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46946324</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46946324</guid></item><item><title><![CDATA[New comment by ezulabs in "Ask HN: How to introduce Claude Code to a team?"]]></title><description><![CDATA[
<p>sorry for my late response, missed your comment.<p>I can definetly help for that too, feel free reach to talk, my email is in my profile.</p>
]]></description><pubDate>Wed, 04 Feb 2026 06:08:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=46882067</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46882067</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46882067</guid></item><item><title><![CDATA[New comment by ezulabs in "Ask HN: Is Cursor still working for you?"]]></title><description><![CDATA[
<p>i will try Claude Code with Opus4.5 on a similar MVP, if it still fails when session becomes higher that means i need to do manual orchestration. I wonder if there is already a pattern people use for that.<p>From my exprience also I agree that Auto on all the time is the way to go for now, 
only pay extra for initial plan nothing else. Also avoid long sessions, after first context summarization Opus4.5 is pretty much done using Cursor, will check how others do and update here.</p>
]]></description><pubDate>Wed, 04 Feb 2026 06:06:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=46882049</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46882049</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46882049</guid></item><item><title><![CDATA[New comment by ezulabs in "Ask HN: Is Cursor still working for you?"]]></title><description><![CDATA[
<p>Tried both, openai models are also good, but something with agent getting out of plan after iterating for me, initial plan says to use xyz library and it uses, later on something goes wrong and fallbacks to a hack or simpler solution despite I correct again and again. I feel like summary of summary for the context causing the issue. Do you use it as snapshot task handling or MVPs? How do you manage long sessions?</p>
]]></description><pubDate>Wed, 04 Feb 2026 05:53:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=46881969</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46881969</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46881969</guid></item><item><title><![CDATA[Ask HN: Is Cursor still working for you?]]></title><description><![CDATA[
<p>I spent $1.5K using Cursor with Opus4.5 to test some MVP ideas.<p>It starts really well and looking promising, but after that you burn all your tokens and energy to make sure agents still sticks to the plan.<p>If it hits a wall, all a sudden it does stupid hacks. I just canceled my subscription and moving on, what else I should try?<p>Did you also eperienced gambling like effect, you keep increasing the spend limit by $50 by thinking this will carry me to a solution that will let me make money with this MVP?<p>What am i missing?</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46877229">https://news.ycombinator.com/item?id=46877229</a></p>
<p>Points: 3</p>
<p># Comments: 4</p>
]]></description><pubDate>Tue, 03 Feb 2026 21:00:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=46877229</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46877229</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46877229</guid></item><item><title><![CDATA[New comment by ezulabs in "Ask HN: Who wants to be hired? (February 2026)"]]></title><description><![CDATA[
<p>Location: Europe (GMT+3)<p>Remote: Yes (4-hour daily overlap with US time zones)<p>Willing to relocate: No<p>Technologies: Python, TypeScript, LLM APIs (Claude, OpenAI), RAG workflows, prompt engineering, gRPC, Docker, Kubernetes, PostgreSQL, Redis, React, Next.js, TensorFlow, Java/Kotlin, C/C++<p>Résumé/CV: <a href="https://www.ezulabs.com" rel="nofollow">https://www.ezulabs.com</a><p>GitHub: <a href="https://github.com/ezulabs" rel="nofollow">https://github.com/ezulabs</a><p>Email: contact@ezulabs.com</p>
]]></description><pubDate>Mon, 02 Feb 2026 19:04:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=46859840</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46859840</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46859840</guid></item><item><title><![CDATA[Show HN: Yaoclaw (Yet Another Open Claw)AI agent that runs cmds in macOS sandbox]]></title><description><![CDATA[
<p>(Yes, the name keeps the "Yet Another" tradition alive. YAML did it, YACC did it, now YAOC. Someone had to.)<p>This whole thing was vibe coded – $99 in tokens later, you can save that and just use your local LLM instead.<p>Shipping before bed because my agent can't work autonomously at night yet, and I know someone would release this while I'm sleeping.<p><a href="https://github.com/ezulabs/yaoclaw" rel="nofollow">https://github.com/ezulabs/yaoclaw</a></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46859697">https://news.ycombinator.com/item?id=46859697</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 02 Feb 2026 18:53:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=46859697</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46859697</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46859697</guid></item><item><title><![CDATA[Show HN: Skill Generator – Turn terminal workflows into AI agent skills]]></title><description><![CDATA[
<p>Vibe-coded a CLI tool that lets you select commands from your console history using a TUI, auto-recognizes parameters, and generates AI skills for Claude/Cursor.<p><a href="https://www.npmjs.com/package/@ezulabs/skillgen-cli" rel="nofollow">https://www.npmjs.com/package/@ezulabs/skillgen-cli</a><p><a href="https://github.com/ezulabs/skillgenerator/" rel="nofollow">https://github.com/ezulabs/skillgenerator/</a></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46738332">https://news.ycombinator.com/item?id=46738332</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 23 Jan 2026 21:42:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=46738332</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46738332</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46738332</guid></item><item><title><![CDATA[New comment by ezulabs in "Ask HN: How to introduce Claude Code to a team?"]]></title><description><![CDATA[
<p>This is something I can help with - happy to do a free session to talk through onboarding strategies for your team. Feel free to reach out, contact info is in my profile.</p>
]]></description><pubDate>Fri, 23 Jan 2026 19:53:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=46737017</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46737017</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46737017</guid></item><item><title><![CDATA[New comment by ezulabs in "Show HN: A self-hosting C compiler that runs on a Raspberry Pi Pico"]]></title><description><![CDATA[
<p>Looking for embedded/compiler work. Happy to discuss implementation details.</p>
]]></description><pubDate>Fri, 23 Jan 2026 18:05:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=46735618</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46735618</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46735618</guid></item><item><title><![CDATA[Show HN: A self-hosting C compiler that runs on a Raspberry Pi Pico]]></title><description><![CDATA[
<p>I built a C compiler that runs on a Raspberry Pi Pico ($4, 264KB RAM). 
It compiles C to ARM Thumb and JIT-executes it.<p>It can compile its own source code on the hardware.<p>Full pipeline: preprocessor, parser, type system, 
Thumb-1/Thumb-2 codegen, mark-and-compact GC, USB REPL.<p>Try it: flash the UF2, connect serial (115200), type "help".<p><a href="https://github.com/ezulabs/MicroCC" rel="nofollow">https://github.com/ezulabs/MicroCC</a></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46735154">https://news.ycombinator.com/item?id=46735154</a></p>
<p>Points: 4</p>
<p># Comments: 1</p>
]]></description><pubDate>Fri, 23 Jan 2026 17:27:59 +0000</pubDate><link>https://github.com/ezulabs/MicroCC</link><dc:creator>ezulabs</dc:creator><comments>https://news.ycombinator.com/item?id=46735154</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46735154</guid></item></channel></rss>