<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: _fat_santa</title><link>https://news.ycombinator.com/user?id=_fat_santa</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 18 Nov 2026 05:12:21 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=_fat_santa" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Show HN: Rowbly – A Software Factory Manager]]></title><description><![CDATA[
<p>Hey everyone,<p>I've been very interested in software factories lately but every time I've read about them, I see folks talking alot about high level concepts and the idea of a software factory but never actually walk you through how to set one up. Or if they do walk you through how to set one up, it's always overly complicated and requires a ton of up-front investment to get things running. In response to this I built rowbly, a CLI that tries to make it as easy as possible to understand and setup a software factory.<p>Rowbly at it's core works like a kanban board and each column can contain an optional prompt that instructs an agent what to do when a story is within this column. Once you have some stories on your board you run a supervisor skill that monitors the board for changes and spawns agents to work on stories within each column.<p>The default configuration ships with 5 columns: backlog, refinement, development, review and done. Once a story is moved into refinement, the supervisor automatically dispatches an agent to refine the story based on the instructions in that column. When refinement is finished the ticket is automatically pushed into the development column when another agent is spawned, then into review and finally into done when the PR is merged.<p>While this is a default configuration, things can get much more exotic based on how things are setup. Each column prompt will define where the story goes after it's finished in that column, so you could wire up a very sophisticated setup, review loops, security scans, testing, etc.<p>From a data perspective I tried to keep things as simple as possible, all data is stored in plain markdown and json files in the folder where you initialize rowbly.<p>If you're interested you can run it directly with npx using: `npx rowbly` or install globally with `npm install -g rowbly`. When you run it for the first time, it will walk you through adding stages, prompts and companion skills but all of this can be modified to your liking.<p>Github Repo: <a href="https://github.com/sgolovine/rowbly/" rel="nofollow">https://github.com/sgolovine/rowbly/</a></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50455475">https://news.ycombinator.com/item?id=50455475</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 11 Nov 2026 16:45:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=50455475</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=50455475</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50455475</guid></item><item><title><![CDATA[New comment by _fat_santa in "Tesla to wind down Cybertruck production"]]></title><description><![CDATA[
<p>I have very mixed feelings about the Cybertruck. Personally I absolutely hate it, it's just not my cup of tea and I would never in a million years buy one. However as a general lover of cars, I have to appreciate just how striking the design is and how it was a complete departure from pretty much any other car on the road.<p>There's nothing quite like the Cybertruck and I don't think there ever will be again.</p>
]]></description><pubDate>Fri, 06 Nov 2026 16:09:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=50394203</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=50394203</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50394203</guid></item><item><title><![CDATA[New comment by _fat_santa in "Synaptics Appears to Use Legal Threats to Block Open-Source DisplayLink Driver"]]></title><description><![CDATA[
<p>That's the problem when you have lawyers in charge. To a lawyer, Drivers and Hardware are the same thing: IP. That IP needs to be "protected", period, end of story.</p>
]]></description><pubDate>Wed, 04 Nov 2026 16:50:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=50368277</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=50368277</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50368277</guid></item><item><title><![CDATA[New comment by _fat_santa in "Postman silently auto-installs AI plugins and attempts to share all API data"]]></title><description><![CDATA[
<p>I use hopscotch and highly recommend it. Very similar UI to postman and it just works.</p>
]]></description><pubDate>Tue, 03 Nov 2026 20:10:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=50357495</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=50357495</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50357495</guid></item><item><title><![CDATA[New comment by _fat_santa in "Kentucky man becomes the first humanist granted religious exemption from AI"]]></title><description><![CDATA[
<p>One thing I've seen with AI is AI as used by software developers is quickly diverging from AI that's used by knowledge workers.<p>Knowledge workers use it primarily to "augment" their work, answer questions with AI, get it to create documents, etc. But it's usually 1 individual to 1-2 conversation threads.<p>Meanwhile in software development were running fleets of agents. At work we have it setup where firing off one agent request will eventually lead to like 10-20 AI calls at different parts of the process.<p>I make this distinctions because it changes how each group thinks about AI. For software devs it just feels like "moving up the stack". Yeah you're not writing code anymore but there is still plenty of work to do and problems to solve within your "software factory". Contrast that with knowledge workers that feel like the AI is making all of their decisions for them.<p>I almost think of this as a factory worker versus an artisan. The software devs are "factory workers" where we used to be on the floor but now we're managing the machines that took over the work. There are still tons of interesting problems at that stage and you still feel like you have worth. Contrast that with a knowledge worker that's more of an artisan in this analogy. For them they aren't running a factory but instead watching a robot do the work they used to do while they sit idle and watch it.</p>
]]></description><pubDate>Wed, 28 Oct 2026 15:56:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=50275804</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=50275804</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50275804</guid></item><item><title><![CDATA[New comment by _fat_santa in "Talorys – A self-hosted personal AI agent on Cloudflare's free tier"]]></title><description><![CDATA[
<p>I would define hosting in the cloud as "self-hosting" because you perform the act of hosting that thing and thus have full control over it.<p>Yes it's not the same as hosting as your own hardware but I would argue that it accomplishes the same goals. The goal is to get other people out of your data. With a "service" the underlying company has every incentive to look at your data and use that to improve it's service, but when you host something yourself with a provider, it's in that providers best interest to never look at your data.<p>For me it all comes down to the goals of the people your are doing business with. With Cloudflare at least, their goal is to just upsell me on hosting equipment, they couldn't give a rats ass what I'm hosting on that hardware so long it's not illegal.</p>
]]></description><pubDate>Sat, 10 Oct 2026 14:52:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=50033561</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=50033561</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50033561</guid></item><item><title><![CDATA[New comment by _fat_santa in "You said no MCP"]]></title><description><![CDATA[
<p>Where I found MCP's really useful is integrating with "consumer AI" (chatgpt.com, claude.ai, etc).<p>I'm working on a sideproject called Rowbly[1]. It acts as a sharable data store where LLM's can dump research rather than keeping it in their memory or throwing it into a spreadsheet.<p>At first I thought "I don't need an MCP, I'll just expose a CLI" but that carries a pretty big limitation in that it only works with agents on your computer (Codex, Claude Code, Pi, etc). For the folks on here this is not an issue and is often times preferable but I'm also targeting the average LLM user that primarily interfaces with it via "consumer AI" and with those tools the stuff you can do is very very limited.<p>I still think MCP's have a long way to go maturity wise and hey maybe in a few years we will figure out a better way to do things but for now, if you want to interact with consumer AI apps, there's just no way around using them.<p>[1]: <a href="https://rowbly.com" rel="nofollow">https://rowbly.com</a></p>
]]></description><pubDate>Wed, 30 Sep 2026 15:20:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=49910155</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49910155</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49910155</guid></item><item><title><![CDATA[New comment by _fat_santa in "OpenAI is enlisting an influencer army to make it look 'good for the world'"]]></title><description><![CDATA[
<p>I feel like the "We hacked hugging face" thing and this influencer thing are targeting different things but have the same goal of hyping up the company for the IPO.<p>- The HF incident was to get the attention of investors and convey the message: "we have this incredibly powerful technology, imagine where we will be in 5 years"<p>- With this influencer campaign it's just a drive to get more people to use ChatGPT / sign up to ChatGPT so when IPO time comes, they can show strong user growth.<p>Over the past few months I've seen various reports that OpenAI's financial position isn't great and if those reports have any merit, then likely the higher ups at OpenAI are panicking that they might become a WeWork 2.0. Everything they are doing now is an attempt to justify their $1T valuation to investors during the IPO.</p>
]]></description><pubDate>Wed, 23 Sep 2026 13:50:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=49816183</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49816183</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49816183</guid></item><item><title><![CDATA[New comment by _fat_santa in "AI Has No Wisdom and Neither Will You"]]></title><description><![CDATA[
<p>> The trillion dollar question is how you do this<p>I don't think it's that hard of a question to answer. I've noticed on my team, our thinking has shifted from how do you directly solve a problem, to how you get an agent to effectively solve the problem and not produce slop in the process.<p>One thing that we have done that's probably made the biggest impact is alot more upfront architecture with the knowledge that pretty soon agents will be running wild all over the code. Having worked with these agents for a while now, you get a very good sense of how they will go about solving a problem and the various footguns they will encounter along the way. Editing an AGENTS.md file or building a skill is not nearly as fun as coding by hand but it will pay dividends over and over if you do it right.<p>Another big thing is doing refactoring passes. Early on in our projects our agents generated ALOT of slop and we had to go back and fix alot of it. But every time we did one of these passes, a major aspect was improving agent instructions / skills / etc so it doesn't happen again. It can be a painful process at first but I found that over time, the amount of slop the agent produces goes down by orders of magnitude.<p>I feel like we're still very much programming, but we're now doing it at a "higher level" where we are not writing the code ourselves but instructing the agent to. And IMHO, properly instructing an agent on a production codebase is not a trivial task.</p>
]]></description><pubDate>Tue, 22 Sep 2026 14:06:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=49801527</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49801527</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49801527</guid></item><item><title><![CDATA[New comment by _fat_santa in "AWS says it can't restore some data from mideast facilities struck by Iran"]]></title><description><![CDATA[
<p>I think that's past the point OP was making. Amazon makes some pretty impressive guarantees of data durability but those guarantees only hold up if you take their advice and replicate data to other regions.<p>It's like saying "Oh this car manufacturer claimed that their cars were the safest in the industry but couldn't prevent this driver from flying through the windshield" and omitting the fact the person wasn't wearing a seatbelt.</p>
]]></description><pubDate>Thu, 17 Sep 2026 15:09:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=49741963</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49741963</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49741963</guid></item><item><title><![CDATA[New comment by _fat_santa in "Dystopian Surveillance Is Becoming a Reality"]]></title><description><![CDATA[
<p>They would have to encrypt it in such a way where even if Law Enforcement went to apple with a subpoena, they would not be able to hand over that data at a technical level.<p>The better way IMHO is use local models so data never actually leaves the device.</p>
]]></description><pubDate>Tue, 15 Sep 2026 17:59:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=49716293</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49716293</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49716293</guid></item><item><title><![CDATA[New comment by _fat_santa in "Claude, change the “Add to Cart” button to blue"]]></title><description><![CDATA[
<p>At least with Codex, this has not been my experience at all. It still screws up sure, but in every case I can ask "why did you do this" and it can trace back what made it take that particular decision. Typically it's always that I either didn't specify the problem correctly or made a really dumb mistake (executing the task on the wrong project....did this one yesterday) or it's something within a skill file that instructs it (at which point I fixup the instructions).<p>Once in a blue moon it's actually the model making a material error in it's thinking and I have to go back and redo it.</p>
]]></description><pubDate>Wed, 09 Sep 2026 14:03:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=49626785</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49626785</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49626785</guid></item><item><title><![CDATA[New comment by _fat_santa in "LG TVs caught spying even when offline or on standby"]]></title><description><![CDATA[
<p>Part of the issue is many TV's these days are essentially bricked until you connect them to the internet to "activate".</p>
]]></description><pubDate>Tue, 08 Sep 2026 19:27:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=49615587</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49615587</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49615587</guid></item><item><title><![CDATA[New comment by _fat_santa in "LG TVs caught spying even when offline or on standby"]]></title><description><![CDATA[
<p>I bought a Hisense TV a few years back and when I set it up, I could not proceed without downloading the companion app. I was curious so I called support and told them that I didn't have a phone and asked how I could activate the TV.<p>Support had no answer for me other than "well you need the app". When I told them I didn't have a phone to install it on they just said "no that's not correct, you must have a phone..."</p>
]]></description><pubDate>Tue, 08 Sep 2026 19:21:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=49615463</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49615463</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49615463</guid></item><item><title><![CDATA[New comment by _fat_santa in "Codex outage"]]></title><description><![CDATA[
<p>This is just the 2020's version of "StackOverfow is down"</p>
]]></description><pubDate>Thu, 03 Sep 2026 15:40:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=49551847</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49551847</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49551847</guid></item><item><title><![CDATA[New comment by _fat_santa in "AI Agents and the Refactoring That Never Happens"]]></title><description><![CDATA[
<p>I've personally adopted doing multiple refactoring passes after any large code implementation done by AI. In pretty much any scenario where I'm adding code using AI, it's 1 turn to add the feature and and then another 4-5 turns to refactor and clean everything up.<p>Often times it's not even that the code is bad but rather that it's overengineered. I see it happen so much that I'm tempted to actually go the other way on a toy project. Like what would Claude or Codex come up with if I told it I wanted an enterprise grade, globally scalable, compliant and auditable tic-tac-toe game.</p>
]]></description><pubDate>Wed, 02 Sep 2026 20:43:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=49542269</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49542269</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49542269</guid></item><item><title><![CDATA[New comment by _fat_santa in "Omarchy: Any User Process Can Escalate to Root"]]></title><description><![CDATA[
<p>I just switched over to it from Ubuntu. So far the nice thing is that it gives you a fully decked out hyprland setup without any of the hassle and pretty good UX.<p>The problem I've always had with trying out a tiling window manager like hyprland is you're going to spend a very long time trying to get everything just right. With Omarchy I get a really nice hyprland setup right out of the box.</p>
]]></description><pubDate>Sun, 30 Aug 2026 17:29:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=49500785</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49500785</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49500785</guid></item><item><title><![CDATA[New comment by _fat_santa in "“It works better in the app”"]]></title><description><![CDATA[
<p>I agree, presentation is a big issue with PWA's since you have to know how to add it vs just searching in the app store. I'm sure were going to get a native app eventually, though customers have not asked for one yet and seem to be pretty happy with the PWA.</p>
]]></description><pubDate>Fri, 28 Aug 2026 15:31:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=49480044</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49480044</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49480044</guid></item><item><title><![CDATA[New comment by _fat_santa in "Advertisers Could Soon Demand 'Verified Clicks'"]]></title><description><![CDATA[
<p>A little off topic but for anyone using Thunderbird, I highly recommend BetterUnsubscribe[1] to help combat spam. Since installing I've basically eliminated marketing emails from my inbox. I've used tools like unroll.me in the past but I found that a one-time review doesn't really help much since every signup and every form entry always risks you getting more marketing emails and having to go to another service all the time creates alot of friction. That extension lets you unsubscribe the moment you see a marketing email hit your inbox.<p>[1]: <a href="https://github.com/LucBennett/BetterUnsubscribe" rel="nofollow">https://github.com/LucBennett/BetterUnsubscribe</a></p>
]]></description><pubDate>Fri, 28 Aug 2026 15:24:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=49479947</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49479947</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49479947</guid></item><item><title><![CDATA[New comment by _fat_santa in "Silicon Valley is in denial in face of widespread backlash"]]></title><description><![CDATA[
<p>You must be following the wrong people.</p>
]]></description><pubDate>Fri, 28 Aug 2026 14:42:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=49479269</link><dc:creator>_fat_santa</dc:creator><comments>https://news.ycombinator.com/item?id=49479269</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49479269</guid></item></channel></rss>