<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: RALaBarge</title><link>https://news.ycombinator.com/user?id=RALaBarge</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 05 Jun 2026 03:48:40 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=RALaBarge" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by RALaBarge in "Artificial intelligence is not conscious – Ted Chiang"]]></title><description><![CDATA[
<p>An electric cloud with quantum effects that we also don’t fully understand.  There will always be a layer deeper that we just do not know the effects of or what actually exists there or “under there”.</p>
]]></description><pubDate>Thu, 04 Jun 2026 13:27:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=48398340</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=48398340</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48398340</guid></item><item><title><![CDATA[New comment by RALaBarge in "Prolific Wikipedia editors are threatening to go on strike"]]></title><description><![CDATA[
<p>Billions of people on the planet, and not a single one of them would offer to do it?</p>
]]></description><pubDate>Fri, 29 May 2026 13:16:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=48322727</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=48322727</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48322727</guid></item><item><title><![CDATA[New comment by RALaBarge in "A few words on DS4"]]></title><description><![CDATA[
<p>They never should have trusted Qwark</p>
]]></description><pubDate>Fri, 15 May 2026 10:21:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=48146817</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=48146817</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48146817</guid></item><item><title><![CDATA[New comment by RALaBarge in "I'm going back to writing code by hand"]]></title><description><![CDATA[
<p>And it is only the beginning.</p>
]]></description><pubDate>Mon, 11 May 2026 19:42:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=48099706</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=48099706</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48099706</guid></item><item><title><![CDATA[New comment by RALaBarge in "Shai-Hulud Themed Malware Found in the PyTorch Lightning AI Training Library"]]></title><description><![CDATA[
<p>Yeah then you can version lock changes to one thing post-evaluation vs or even easier as noted above, download the stdlib and host it yourself.</p>
]]></description><pubDate>Fri, 01 May 2026 01:50:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=47970515</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47970515</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47970515</guid></item><item><title><![CDATA[New comment by RALaBarge in "Shai-Hulud Themed Malware Found in the PyTorch Lightning AI Training Library"]]></title><description><![CDATA[
<p>I think we are stuck with LLMs.  They are already in a place where they can find these issues in the first place.  They can access RSS feeds.  You could cron an agent to look to see if you are pwned as frequently as you want at literally almost zero cost.  When you do ingest the libraries, keep a list and of what version and that can help as well.</p>
]]></description><pubDate>Fri, 01 May 2026 01:38:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=47970440</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47970440</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47970440</guid></item><item><title><![CDATA[New comment by RALaBarge in "Running local LLMs offline on a ten-hour flight"]]></title><description><![CDATA[
<p>It’s all about tooling,  if the ai can fetch data it can do something rad with it.  Use something like an ai harness to have an mcp server and other tooling to improve the harness and the tools I made this for my own learning: GitHub.com/ralabarge/beigebox</p>
]]></description><pubDate>Mon, 27 Apr 2026 17:00:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=47924216</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47924216</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47924216</guid></item><item><title><![CDATA[New comment by RALaBarge in "DeepSeek v4"]]></title><description><![CDATA[
<p>Jingoism: Its such a rush!</p>
]]></description><pubDate>Fri, 24 Apr 2026 12:20:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=47889221</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47889221</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47889221</guid></item><item><title><![CDATA[New comment by RALaBarge in "GPT-5.5"]]></title><description><![CDATA[
<p>Check out github.com/ralabarge/beigebox -- OSS AI Harness, started as a way to save all of my data but has agentic features, MCP server, point it at any endpoint (or use any front end with it as well, transparent middleware)<p>So far what I am finding is that you just get the basics working and then use the tool and inference to improve the tool.</p>
]]></description><pubDate>Thu, 23 Apr 2026 22:56:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=47883316</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47883316</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47883316</guid></item><item><title><![CDATA[New comment by RALaBarge in "GPT-5.5"]]></title><description><![CDATA[
<p>We totally agree.<p>That's what I've been heads down, HUNGRY, working on, looking for investors and founding engineers pst: <a href="https://heymanniceidea.com" rel="nofollow">https://heymanniceidea.com</a> (disclaimer: I am not associated with heymanniceidea.com)</p>
]]></description><pubDate>Thu, 23 Apr 2026 22:52:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=47883279</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47883279</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47883279</guid></item><item><title><![CDATA[New comment by RALaBarge in "GPT-5.5"]]></title><description><![CDATA[
<p>YMMV but Grok 4.1 Fast can usually find via static analysis a few things that other models dont seem to catch with the same prompt</p>
]]></description><pubDate>Thu, 23 Apr 2026 22:50:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=47883255</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47883255</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47883255</guid></item><item><title><![CDATA[New comment by RALaBarge in "N-Day-Bench – Can LLMs find real vulnerabilities in real codebases?"]]></title><description><![CDATA[
<p>I can say without a shadow of a doubt: yes.</p>
]]></description><pubDate>Tue, 14 Apr 2026 11:51:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=47764402</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47764402</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47764402</guid></item><item><title><![CDATA[New comment by RALaBarge in "All elementary functions from a single binary operator"]]></title><description><![CDATA[
<p>I am like "Yeah ok, use the Arcee Trinity models!" and its like, you got it boss, 3 opus agents in parallel, got it!</p>
]]></description><pubDate>Mon, 13 Apr 2026 11:55:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=47750726</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47750726</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47750726</guid></item><item><title><![CDATA[New comment by RALaBarge in "The economics of software teams: Why most engineering orgs are flying blind"]]></title><description><![CDATA[
<p>The more I work with AIs (I build AI harnessing tools), the more I see similarities between the common attention failures that humans make.  I forgot this one thing and it fucks everything up, or you just told me but I have too much in my mind as context that I forget that piece, or even in the case of Claude last night attesting to me while I am ordering it around that it cannot SSH into another server but I find it SSHing into said server about the 5th time I come back with traceback and it just fixes it!<p>All of these things human do, and i don't think we can attribute it directly to language itself, its attention and context and we both have the same issues.</p>
]]></description><pubDate>Mon, 13 Apr 2026 11:52:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=47750702</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47750702</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47750702</guid></item><item><title><![CDATA[New comment by RALaBarge in "Show HN: Keeper – embedded secret store for Go (help me break it)"]]></title><description><![CDATA[
<p>Not sure, I've seen common things like this pop up a lot too, the same errors being tripped over.  I'm not sure if it is a context thing or just a limitation of how the models work presently?  For stuff that I'm using myself, I will run these through like the top 10 reasoning models on OR and just see where everything pans out.<p>Edit: here is an example of the process and output with something I put together the other day: <a href="https://github.com/RALaBarge/garlicpress/blob/master/portfolio/COMPLETE_RESULTS.md" rel="nofollow">https://github.com/RALaBarge/garlicpress/blob/master/portfol...</a></p>
]]></description><pubDate>Fri, 10 Apr 2026 11:47:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=47716662</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47716662</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47716662</guid></item><item><title><![CDATA[New comment by RALaBarge in "Show HN: Keeper – embedded secret store for Go (help me break it)"]]></title><description><![CDATA[
<p>Hey I ran this request through my AI harness (beigeboxoss.com), first with a smaller local model and then validated with Trinity Large via OR.  <a href="https://github.com/agberohq/keeper/issues/2" rel="nofollow">https://github.com/agberohq/keeper/issues/2</a>  -- YMMV but wanted something to do with my coffee, thanks!</p>
]]></description><pubDate>Fri, 10 Apr 2026 11:41:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=47716616</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47716616</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47716616</guid></item><item><title><![CDATA[New comment by RALaBarge in "System Card: Claude Mythos Preview [pdf]"]]></title><description><![CDATA[
<p>Exploits in embedded systems that will never be properly updated is just one thing I can think of if one really thought about it.</p>
]]></description><pubDate>Tue, 07 Apr 2026 23:42:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=47682770</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47682770</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47682770</guid></item><item><title><![CDATA[New comment by RALaBarge in "Project Glasswing: Securing critical software for the AI era"]]></title><description><![CDATA[
<p>Botnet city: where everyone's a botnet, and the DDoS dont matter!</p>
]]></description><pubDate>Tue, 07 Apr 2026 23:39:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=47682747</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47682747</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47682747</guid></item><item><title><![CDATA[New comment by RALaBarge in "Project Glasswing: Securing critical software for the AI era"]]></title><description><![CDATA[
<p>I need to start SaaS for getting people to start doing lunges and squats so they can carry others around on their back, I need a founding engineer, a founding marketer, and 100m hard currency.</p>
]]></description><pubDate>Tue, 07 Apr 2026 23:34:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=47682699</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47682699</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47682699</guid></item><item><title><![CDATA[New comment by RALaBarge in "Running out of disk space in production"]]></title><description><![CDATA[
<p>Wait until you run out of inodes!</p>
]]></description><pubDate>Tue, 07 Apr 2026 15:03:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=47676506</link><dc:creator>RALaBarge</dc:creator><comments>https://news.ycombinator.com/item?id=47676506</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47676506</guid></item></channel></rss>