<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: dumbfoundded</title><link>https://news.ycombinator.com/user?id=dumbfoundded</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 21 Oct 2026 07:37:32 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=dumbfoundded" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by dumbfoundded in "Ask HN: What are you working on? (September 2026)"]]></title><description><![CDATA[
<p>I created an ai cross-stitch pattern generating tool: <a href="https://stitchwink.com/admin" rel="nofollow">https://stitchwink.com/admin</a><p>If you try to use image generation directly, you don't get real patterns. StitchWink makes real patterns that you can also edit manually or through text/images with AI.</p>
]]></description><pubDate>Mon, 14 Sep 2026 19:47:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=49702849</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=49702849</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49702849</guid></item><item><title><![CDATA[New comment by dumbfoundded in "Show HN: Stitchwink – Cross-stitch pattern making with AI"]]></title><description><![CDATA[
<p>I just tried a pure text: "Can you make a cross stitch of a very round and big tuxedo cat? He should be laying down and look very confident"<p>I got this one: <a href="https://stitchwink.com/share/7a9c5c69-b45a-4d4c-9fb0-2792189eb738" rel="nofollow">https://stitchwink.com/share/7a9c5c69-b45a-4d4c-9fb0-2792189...</a><p>It definitely takes a few tries sometimes to get it right. I've been having trouble with a "brain in a jar" for halloween right now.</p>
]]></description><pubDate>Fri, 11 Sep 2026 01:37:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=49652504</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=49652504</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49652504</guid></item><item><title><![CDATA[New comment by dumbfoundded in "Show HN: Stitchwink – Cross-stitch pattern making with AI"]]></title><description><![CDATA[
<p>I haven't tried it in firefox. Thank you for finding that.<p>Sometimes it does take a couple tries to get a good result but I just tried my tuxedo cat (a close up of him sitting on my car) and it seemed to work pretty well: <a href="https://stitchwink.com/share/5bf3d6f0-f064-4476-83e6-f75c3a31c855" rel="nofollow">https://stitchwink.com/share/5bf3d6f0-f064-4476-83e6-f75c3a3...</a></p>
]]></description><pubDate>Fri, 11 Sep 2026 00:22:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=49651939</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=49651939</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49651939</guid></item><item><title><![CDATA[Show HN: Stitchwink – Cross-stitch pattern making with AI]]></title><description><![CDATA[
<p>My wife has been cross stitching since she was a child and I wanted to make a tool where she could generate her own custom patterns: <a href="https://stitchwink.com/" rel="nofollow">https://stitchwink.com/</a><p>You can try chatgpt or other AI tools but the problem is that they don't create real patterns. They look good at first glance but it's not actually a physically realizable pattern when you look at the details.<p>The way it works is pretty simple, you use text (& optional images) to create and edit patterns. There's also a built in editor to manually change any of the stitches. It's not perfect but with a few manual edits, she's been able to create some awesome patterns.<p>Here are a few one the ones she's made:
<a href="https://stitchwink.com/share/8efdff80-2a21-4e7f-8122-553ca947c983" rel="nofollow">https://stitchwink.com/share/8efdff80-2a21-4e7f-8122-553ca94...</a>
<a href="https://stitchwink.com/share/ab47a0bf-afbc-44ff-90ad-912853577617" rel="nofollow">https://stitchwink.com/share/ab47a0bf-afbc-44ff-90ad-9128535...</a>
<a href="https://stitchwink.com/share/201fa791-39a1-4684-9f3e-2539a620d489" rel="nofollow">https://stitchwink.com/share/201fa791-39a1-4684-9f3e-2539a62...</a>
<a href="https://stitchwink.com/share/dcdf06be-fe2b-4353-85e5-3eede41ffa72" rel="nofollow">https://stitchwink.com/share/dcdf06be-fe2b-4353-85e5-3eede41...</a></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49650254">https://news.ycombinator.com/item?id=49650254</a></p>
<p>Points: 1</p>
<p># Comments: 4</p>
]]></description><pubDate>Thu, 10 Sep 2026 21:15:34 +0000</pubDate><link>https://stitchwink.com</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=49650254</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49650254</guid></item><item><title><![CDATA[What we measured after moving 100B tokens/week to open-weight models]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.ito.ai/blog/measuring-100b-tokens-week-open-weight-models">https://www.ito.ai/blog/measuring-100b-tokens-week-open-weight-models</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48897660">https://news.ycombinator.com/item?id=48897660</a></p>
<p>Points: 6</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 13 Jul 2026 19:33:53 +0000</pubDate><link>https://www.ito.ai/blog/measuring-100b-tokens-week-open-weight-models</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=48897660</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48897660</guid></item><item><title><![CDATA[New comment by dumbfoundded in "Show HN: Richest people in the world by wealth creation instead of ownership"]]></title><description><![CDATA[
<p>It's absolutely wrong. We also have: Alexander Fleming, Howard Florey & Ernst Chain who contributed significantly to antibiotics.<p>You could even add politicians. How much wealth did FDR create?</p>
]]></description><pubDate>Sat, 11 Jul 2026 16:21:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=48873373</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=48873373</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48873373</guid></item><item><title><![CDATA[New comment by dumbfoundded in "Anyone else get a vague GitHub shakedown notice?"]]></title><description><![CDATA[
<p>It sounds like they gave you a feature for free you didn't want, and now are trying to charge for it. Very much a dark pattern.</p>
]]></description><pubDate>Fri, 10 Jul 2026 17:59:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=48863142</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=48863142</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48863142</guid></item><item><title><![CDATA[New comment by dumbfoundded in "How version control will evolve for the agent boom"]]></title><description><![CDATA[
<p>Have you tried creating skills for your agents to follow your patterns?</p>
]]></description><pubDate>Fri, 10 Jul 2026 16:30:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=48862147</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=48862147</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48862147</guid></item><item><title><![CDATA[New comment by dumbfoundded in "The next era of AI is about infrastructure, not just models"]]></title><description><![CDATA[
<p>Will organizations want to control their own proxy or use OpenRouter?</p>
]]></description><pubDate>Thu, 09 Jul 2026 21:02:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=48852330</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=48852330</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48852330</guid></item><item><title><![CDATA[Show HN: Moo, Git versions code, moo versions machines]]></title><description><![CDATA[
<p>I'm Evan, CTO of Ito (ito.ai). We do code review that actually runs your code. When we're developing locally, we run lots of coding agents in parallel against the same repo, and we kept hitting the same wall: git worktrees isolate files, but the database, ports, and services all collide.<p>Moo is a brand new internal tool we use to moove faster and thought we'd share it.<p>Every branch or agent attempt gets its own isolated Linux machine, and the machine's state is versioned with your repo. Moo save snapshots the runtime tagged with the current commit. Check out an old SHA, run moo new, and you boot the exact runtime that existed there.<p>It's microVMs with copy-on-write (CoW) disks under the hood. Forking a 20 GB environment is <500ms.<p>Right now it's only macOS Apple Silicon only due to depending on libkrun and APFS clonefile.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48835456">https://news.ycombinator.com/item?id=48835456</a></p>
<p>Points: 9</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 08 Jul 2026 18:22:58 +0000</pubDate><link>https://github.com/heyito/moo</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=48835456</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48835456</guid></item><item><title><![CDATA[New comment by dumbfoundded in "Ask HN: What are you working on? (June 2026)"]]></title><description><![CDATA[
<p>I'm working on Ito.ai : <a href="https://www.ito.ai/" rel="nofollow">https://www.ito.ai/</a><p>It's Agentic QA + auto-provisioning sandboxes. Makes it plug and play to do code reviews that actually run your code instead of looking at it really hard. B/c the agents control all of the environment (ie running all of the services), it's able to collect runtime evidence about pretty much everything.<p>A couple open source examples: (Excalidraw) <a href="https://app.ito.ai/share/d1cb1475-fbe5-4c71-901b-409ba2aa6d6b?tab=details" rel="nofollow">https://app.ito.ai/share/d1cb1475-fbe5-4c71-901b-409ba2aa6d6...</a> & (n8n) <a href="https://app.ito.ai/share/bb7d73aa-fd08-482d-9938-87938e2a2322?tab=details&testCase=d11b5ee5-ce40-4c52-8c8e-1e864031d5c8" rel="nofollow">https://app.ito.ai/share/bb7d73aa-fd08-482d-9938-87938e2a232...</a></p>
]]></description><pubDate>Sun, 14 Jun 2026 18:15:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=48530655</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=48530655</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48530655</guid></item><item><title><![CDATA[New comment by dumbfoundded in "Quantum computing bombshells that are not April Fools"]]></title><description><![CDATA[
<p>If the question is storage, bitcoin itself provides a perfectly good mechanism. idk the exact costs but it'd be in the range of ~$0.45 to store a commitment. That's cheap enough to enable good users with small numbers of keys but also expensive enough to prevent spam. It's kind of the whole point of blockchains.<p>As for verification being expensive, it sounds like you don't know the actual costs. It's basically a hash. Finding the pre-image of a hash is very expensive to the point of being impossible. Verifying a pre-image + hash function = a hash is extremely cheap. That's the whole point of 1-way functions. Bitcoin itself is at ~1000 EH/s (exahashes per second)<p>Again, this isn't a technical problem. It's a coordination problem.</p>
]]></description><pubDate>Thu, 02 Apr 2026 20:47:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=47619946</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=47619946</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47619946</guid></item><item><title><![CDATA[New comment by dumbfoundded in "Quantum computing bombshells that are not April Fools"]]></title><description><![CDATA[
<p>I don't think you're understanding how cryptography works. A commitment is basically a hash that is both binding and hiding. In this example it's probably easiest to think of it as a hash. So you hash your post-quantum public key (something like falcon-512) and then sign that hash with your actual bitcoin private key (ecdsa, discrete-log, not quantum safe) and then publish that message to the bitcoin network. Then quantum happens at some point and bitcoin needs to migrate but where do funds go? Well you reveal the post-quantum public key and then you can prove that funds from the ecdsa key should go there. From a technical perspective, this is a complete and fool proof system. DoSing isn't really a concern if you publish to the actual bitcoin network and it's impossible for someone to use up the key space (2^108 combinations at least).<p>The reason this is a dumb idea is because coordination and timing. When does the cutover happen? Who decides which transactions no longer count as they were "broken" b/c of quantum computing? The idea is broken but not from technical fundamentals.</p>
]]></description><pubDate>Thu, 02 Apr 2026 16:50:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=47616911</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=47616911</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47616911</guid></item><item><title><![CDATA[New comment by dumbfoundded in "Show HN: Ito AI, open source smart dictation"]]></title><description><![CDATA[
<p>It's an electron app but latency sensitive bits are written in rust: <a href="https://github.com/heyito/ito/tree/dev/native/audio-recorder" rel="nofollow">https://github.com/heyito/ito/tree/dev/native/audio-recorder</a></p>
]]></description><pubDate>Thu, 06 Nov 2025 18:59:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=45838924</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=45838924</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45838924</guid></item><item><title><![CDATA[Show HN: Ito AI, open source smart dictation]]></title><description><![CDATA[
<p>Hey HN, I’m Evan, cofounder and CTO of Ito AI.<p>Ito is a voice to intent app that turns what you say into structured text: notes, messages, code, or any text field you’re working in. It’s designed to feel fast, clean, and distraction free. It works on Windows and Mac.<p>Most speech tools are either locked inside closed systems or overly complicated & overly parameterized and difficult to setup. We wanted something that works like a native app, looks good, and stays transparent about your data. Ito is open-source under GPL-3.<p>Our focus is simplicity and polish. You can use a few different models and providers but we're still working on an entirely local first experience. It's also pretty easy to host yourself if you want to avoid our infra all together.<p>We’re still early, but it’s already stable enough that I use it daily for coding notes, writing, and quick thoughts between tasks.<p>Try it here: <a href="https://ito.ai" rel="nofollow">https://ito.ai</a><p>Code: <a href="https://github.com/heyito/ito" rel="nofollow">https://github.com/heyito/ito</a><p>Would love feedback, critiques, and ideas for integrations.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45838634">https://news.ycombinator.com/item?id=45838634</a></p>
<p>Points: 16</p>
<p># Comments: 21</p>
]]></description><pubDate>Thu, 06 Nov 2025 18:34:20 +0000</pubDate><link>https://ito.ai</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=45838634</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45838634</guid></item><item><title><![CDATA[New comment by dumbfoundded in "Canaries in the Coal Mine? Recent Employment Effects of AI [pdf]"]]></title><description><![CDATA[
<p>Corporations will require everything going through an LLM to meet company standards.</p>
]]></description><pubDate>Thu, 28 Aug 2025 05:19:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=45048661</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=45048661</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45048661</guid></item><item><title><![CDATA[New comment by dumbfoundded in "Vibe coding creates a bus factor of zero"]]></title><description><![CDATA[
<p>It's definitely a middle ground, but PR reviews, are not perfect. So it's easy to miss a lot of things and to have a lot of extra baggage. From reviewing code it's not always easy to tell exactly what's necessary or duplicate. So I agree, this is a middle ground of using LLMs to be more productive. Removing one bad line of code is worth adding a hundred good lines of code.</p>
]]></description><pubDate>Thu, 21 Aug 2025 00:42:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=44967977</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=44967977</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44967977</guid></item><item><title><![CDATA[New comment by dumbfoundded in "Training for one trillion parameter model backed by Intel and US govt has begun"]]></title><description><![CDATA[
<p>The difference between a government and a corporation is the ability to use violence. A government is just a corporation with a monopoly on violence (police, military, jails...). The structure of how people are organized is more significant. Are we talking about a dictatorship or a functioning democracy? Are we discussing a non-profit or a publicly listed company?</p>
]]></description><pubDate>Fri, 24 Nov 2023 16:09:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=38405336</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=38405336</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38405336</guid></item><item><title><![CDATA[New comment by dumbfoundded in "Math proof draws new boundaries around black hole formation"]]></title><description><![CDATA[
<p>I'm not sure. Somewhere around 10^12 kg of initial mass would be evaporating today (1). So perhaps there is no meaningful minimum, only a minimum initial mass. If it's just about to evaporate, it could perhaps be arbitrarily small. Earth is ~10^25 for reference.<p>(1) <a href="https://en.wikipedia.org/wiki/Micro_black_hole#Expected_observable_effects" rel="nofollow noreferrer">https://en.wikipedia.org/wiki/Micro_black_hole#Expected_obse...</a></p>
]]></description><pubDate>Thu, 17 Aug 2023 06:53:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=37158123</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=37158123</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37158123</guid></item><item><title><![CDATA[New comment by dumbfoundded in "Math proof draws new boundaries around black hole formation"]]></title><description><![CDATA[
<p>It's not a practical possibility. The black hole wouldn't last long and would be too small to actually absorb anything. It's the equivalent of asking if a nuke would set the atmosphere on fire.<p>Even a "large"ish primordial black hole would probably just pass straight through the Earth without anyone noticing.<p>Strange matter on the other hand...</p>
]]></description><pubDate>Wed, 16 Aug 2023 19:30:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=37152393</link><dc:creator>dumbfoundded</dc:creator><comments>https://news.ycombinator.com/item?id=37152393</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37152393</guid></item></channel></rss>