<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: 2ero_wf</title><link>https://news.ycombinator.com/user?id=2ero_wf</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 18 Nov 2026 04:15:44 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=2ero_wf" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by 2ero_wf in "Ask HN: What are you building – I'd try it, pay for it, or even star your repo"]]></title><description><![CDATA[
<p>manage 10+ agents? want to move things off your laptop? have personal agents still running locally? 40+ projects in your github repo with no place to host and share?<p>A VM Cloud for hosting your agents, software with built-in terminal first remote ADE.<p>build, host, share, 10X faster<p><a href="https://workspace.shako.dev/" rel="nofollow">https://workspace.shako.dev/</a></p>
]]></description><pubDate>Tue, 10 Nov 2026 19:45:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=50445332</link><dc:creator>2ero_wf</dc:creator><comments>https://news.ycombinator.com/item?id=50445332</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50445332</guid></item><item><title><![CDATA[New comment by 2ero_wf in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>i use remote ADE in a VM cluster, build things remotely and host right after development. i need my laptop to play world of warcraft, 10+ agents eats 14GB out of 16GB, thus i had to move.</p>
]]></description><pubDate>Tue, 10 Nov 2026 19:39:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=50445235</link><dc:creator>2ero_wf</dc:creator><comments>https://news.ycombinator.com/item?id=50445235</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50445235</guid></item><item><title><![CDATA[New comment by 2ero_wf in "OpenClaw SaaS?"]]></title><description><![CDATA[
<p>i can set it up for you and host it for you on my cloud, are u interested?
i only charge hosting cost, you take care of the maintainence after initial setup, can ask me for tech support.</p>
]]></description><pubDate>Tue, 10 Nov 2026 19:37:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=50445206</link><dc:creator>2ero_wf</dc:creator><comments>https://news.ycombinator.com/item?id=50445206</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50445206</guid></item><item><title><![CDATA[New comment by 2ero_wf in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>are you running all these on your laptop?<p>i now am fully onto agentic development environment that runs remotely and where i can host my personal agents(just like claude co-work but called hermes). managing 5-10 agents at the same place. it doubled my productivity and i can close my lid when i go to bed.<p>i only keep the best coding agent sub(claude), and use pi with deepseek as backup. i don't think you need that many subs.</p>
]]></description><pubDate>Tue, 10 Nov 2026 19:35:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=50445173</link><dc:creator>2ero_wf</dc:creator><comments>https://news.ycombinator.com/item?id=50445173</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50445173</guid></item><item><title><![CDATA[New comment by 2ero_wf in "Ask HN: What are you working on? (November 2026)"]]></title><description><![CDATA[
<p>Interesting idea, i tried it, your left & right are reversed.<p>is this open sourced?</p>
]]></description><pubDate>Tue, 10 Nov 2026 19:29:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=50445082</link><dc:creator>2ero_wf</dc:creator><comments>https://news.ycombinator.com/item?id=50445082</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50445082</guid></item><item><title><![CDATA[New comment by 2ero_wf in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>i just give agent a VM, whether the agent is hermes or claude code.
i made sure the VM sleeps when idle, and i made sure i can copy, resize, delete VM when i want to change my setup.<p>I have 6 VMs hosting claude code coding agent, 2 hermes agent, 1 pi agent when i am out of claude sub, 2 other host some personal-saas softwares. all in VMs.</p>
]]></description><pubDate>Mon, 09 Nov 2026 18:04:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=50429130</link><dc:creator>2ero_wf</dc:creator><comments>https://news.ycombinator.com/item?id=50429130</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50429130</guid></item><item><title><![CDATA[New comment by 2ero_wf in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>I am building this domain, and the cheapest available you can find on the internet per GB of RAM, native ssh, port sharing, a lean agent development environment on top.
If you are interested, i'd like to invite you to be a beta tester. would you be interested?</p>
]]></description><pubDate>Fri, 06 Nov 2026 00:08:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=50386408</link><dc:creator>2ero_wf</dc:creator><comments>https://news.ycombinator.com/item?id=50386408</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50386408</guid></item><item><title><![CDATA[New comment by 2ero_wf in "Muse – Meta’s personal AI agent"]]></title><description><![CDATA[
<p>Tried it, it's not designed by someone who need the software. tech is solid.<p>As a busy professional, i hate repeated shit work, kids' extra currilulum sign up, lunch order; insurance calls; things i don't want to do but have to do;<p>buying sneakers or good piece of steak actually are relaxing activity for myself.<p>there are some very common shitful painful things people want automated, but the app did none of them.</p>
]]></description><pubDate>Thu, 10 Sep 2026 05:13:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=49638697</link><dc:creator>2ero_wf</dc:creator><comments>https://news.ycombinator.com/item?id=49638697</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49638697</guid></item><item><title><![CDATA[New comment by 2ero_wf in "Muse – Meta’s personal AI agent"]]></title><description><![CDATA[
<p>any expert knows their harness design?
browser activity is long and isolated task ( potentially a subagent? )<p>it's known hard to surface subagent HITL back to main agent seamlessly. how is that done?</p>
]]></description><pubDate>Thu, 10 Sep 2026 04:41:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=49638491</link><dc:creator>2ero_wf</dc:creator><comments>https://news.ycombinator.com/item?id=49638491</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49638491</guid></item><item><title><![CDATA[Ask HN: Do you need go-to-market strategy at early stage?]]></title><description><![CDATA[
<p>My startup is pre-revenue. Last week i was in one of the local AI Startup meet up, and attended some GTM office hours hosted by some folks from big company marketing team.<p>Was told Go to market strategy is necessary, need professional helps, it will guide how i run growth campaigns(cold emailing), branding(color). and that i am not able to aquire customer maybe because i don't have a go-to-market strategy, and later on followed by a invitation for deeper GTM consultation(paid).<p>Because i haven't successfully gotten any customer, i cannot rule-out this possibility. But i've watched almost all YC videos on how to get first customer,<p>1. having a GTM is never mentioned not to mention as a mandate<p>2. in fact, from one of the Aaron Epstein's video, a sincere, manual, email works best, with a razor sharp ICP, this doesn't sound GTM at all, it's just doing this one, hard-coded step, no strategy is needed.<p>I would love to hear from you folks on your take before i either go work with these GTM folks, or follow the linear, hardcore step that YC/others have recommended.<p>Time is money thus asking for advices.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48456858">https://news.ycombinator.com/item?id=48456858</a></p>
<p>Points: 2</p>
<p># Comments: 4</p>
]]></description><pubDate>Tue, 09 Jun 2026 05:27:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=48456858</link><dc:creator>2ero_wf</dc:creator><comments>https://news.ycombinator.com/item?id=48456858</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48456858</guid></item><item><title><![CDATA[New comment by 2ero_wf in "Ask HN: How do you choose a model for a task?"]]></title><description><![CDATA[
<p>Sonnet 4.6 for coding, some initial research
Deepseek(V4 pro, R1) for building actual product
keyword search/summary, cheap model like deepseek v4-flash ( i'd do this if i know the task needs 0 reasoning )<p>other models are mostly for cross-validation</p>
]]></description><pubDate>Tue, 12 May 2026 22:06:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=48115231</link><dc:creator>2ero_wf</dc:creator><comments>https://news.ycombinator.com/item?id=48115231</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48115231</guid></item><item><title><![CDATA[New comment by 2ero_wf in "Ask HN: Which LLM are you using to evaluate your ideas?"]]></title><description><![CDATA[
<p>I use Claude for initial validation.
Then move to deepseek
my stack is langchain, complexity sucks, but once you setup the skills, claude.md, AI is ok dealing with it, langchain makes it easy to switch LLMs. some minor issues here and there, e.g. different models have different messaging format.<p>so far so good.</p>
]]></description><pubDate>Tue, 12 May 2026 19:03:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=48112819</link><dc:creator>2ero_wf</dc:creator><comments>https://news.ycombinator.com/item?id=48112819</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48112819</guid></item></channel></rss>