<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: petargyurov</title><link>https://news.ycombinator.com/user?id=petargyurov</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 18 Apr 2026 09:43:23 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=petargyurov" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by petargyurov in "Ask HN: What Are You Working On? (April 2026)"]]></title><description><![CDATA[
<p>I recently built Cranki [0], a free little PWA that generates crosswords using your Anki flashcard lists. It's aimed at language learners (who find flashcards boring and crossword fun!).<p>To be honest I built it just for me and then decided it might be useful for others.<p>It's all local, no server, no database, etc. Mobile and desktop friendly.<p>[0] <a href="https://cranki.app" rel="nofollow">https://cranki.app</a></p>
]]></description><pubDate>Mon, 13 Apr 2026 06:41:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=47748476</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=47748476</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47748476</guid></item><item><title><![CDATA[New comment by petargyurov in "Ask HN: What are you building that's not AI related?"]]></title><description><![CDATA[
<p>I recently built Cranki [0], a free little PWA that generates crosswords using your Anki flashcard lists. It's aimed at language learners (who find flashcards boring and crossword fun!). To be honest I built it just for me and then decided it might be useful for others.<p>It's all local, no server, no database, etc. Mobile and desktop friendly.<p>I did build it with the help of AI, but no AI inside the actual thing.<p>[0] <a href="https://cranki.app" rel="nofollow">https://cranki.app</a></p>
]]></description><pubDate>Thu, 09 Apr 2026 09:50:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=47701416</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=47701416</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47701416</guid></item><item><title><![CDATA[Show HN: I made a crossword app for language learners]]></title><description><![CDATA[
<p>Hi HN!<p>In the last couple of weeks I've been working on Cranki:<p>Cranki = Crosswords + Anki. (It's a stupid name tbh, haha)<p>I like doing crosswords in Spanish (to learn vocab) but none of the apps out there allowed me to use my own list of words that I come across. So I built one instead.<p>It's entirely client-side. No server, no database, no accounts, etc. Your words and stats are stored in local storage.<p>I built this for myself but let me know if you like it!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47660065">https://news.ycombinator.com/item?id=47660065</a></p>
<p>Points: 8</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 06 Apr 2026 12:31:16 +0000</pubDate><link>https://cranki.app/</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=47660065</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47660065</guid></item><item><title><![CDATA[Show HN: Cranki – Crosswords meet Anki flashcards]]></title><description><![CDATA[
<p>Hi HN!<p>I am sure most of you have heard of Anki flashcards? Using spaced-repetition is one of the best ways to learn more vocabulary when learning a language.<p>However, I find flashcards super boring. I've been playing some crossword games in my target language, Spanish, but I wished that I could use my custom list of words that I've come across instead of random words.<p>That gave me the idea to create this mini-app. It's super simple. Add your words and you get <i>unlimited</i> crosswords with spaced-repetition! If you get a word right you won't see it for the next few days.<p>Works with most languages (I doubt it works with Arabic or Chinese for example).<p>You can add words one by one or import a CSV (just make sure to follow the columns: word, answer)<p>It's a PWA, so you should be able to install it via your browser and it should work offline!<p>There's still some bugs and QoL things to add but let me know what you think!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47545102">https://news.ycombinator.com/item?id=47545102</a></p>
<p>Points: 4</p>
<p># Comments: 1</p>
]]></description><pubDate>Fri, 27 Mar 2026 16:46:43 +0000</pubDate><link>https://cranki.app</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=47545102</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47545102</guid></item><item><title><![CDATA[New comment by petargyurov in "Show HN: Cranki – Crosswords meet Anki flashcards"]]></title><description><![CDATA[
<p>Thanks for the feedback!<p>Yeah, it's more of a flashcard-crossword rather than a real crossword. I will have a think about how I can make the clues more interesting. I wanted to make this simple to use (and free) so adding an LLM in there might complicate things.<p>Thanks for trying it!</p>
]]></description><pubDate>Fri, 27 Mar 2026 16:44:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=47545075</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=47545075</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47545075</guid></item><item><title><![CDATA[Show HN: Cranki – Crosswords meet Anki flashcards]]></title><description><![CDATA[
<p>Hi HN!<p>I am sure most of you have heard of Anki flashcards? Using spaced-repetition is one of the best ways to learn more vocabulary when learning a language.<p>However, I find flashcards super boring. I've been playing some crossword games in my target language, Spanish, but I wished that I could use my custom list of words that I've come across instead of random words.<p>That gave me the idea to create this mini-app. It's super simple. Add your words and you get *unlimited* crosswords with spaced-repetition! If you get a word right you won't see it for the next few days.<p>Works with any language (I think). You can add words one by one or import a CSV (just make sure to follow the columns: word, answer)<p>It's a PWA, so you should be able to install it via your browser and it should work offline!<p>There's still some bugs and QoL things to add but let me know what you think!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47507128">https://news.ycombinator.com/item?id=47507128</a></p>
<p>Points: 3</p>
<p># Comments: 2</p>
]]></description><pubDate>Tue, 24 Mar 2026 18:33:34 +0000</pubDate><link>https://cranki.app</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=47507128</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47507128</guid></item><item><title><![CDATA[New comment by petargyurov in "I built a game where you argue consumer rights against AI bots"]]></title><description><![CDATA[
<p>I like this but after 3-4 messages I got the AI to agree that my flight should be refunded yet the confidence was not zero. The tips just said to keep explaining why the particular law applies in my situation but I already kinda did that.</p>
]]></description><pubDate>Fri, 20 Mar 2026 16:31:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=47456958</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=47456958</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47456958</guid></item><item><title><![CDATA[New comment by petargyurov in "Launch HN: Voltair (YC W26) – Drone and charging network for power utilities"]]></title><description><![CDATA[
<p>At my job [0] we work in this exact space, but on the data analytics side of things. We build computer vision pipelines for corrosion, components, defects, etc. We process imagery from drones, helis and satellite.<p>This is a tough problem to solve and for a lot of operators ultimately comes down to cost.<p>We're based in the UK but reach out if you wanna chat!<p>[0] <a href="https://keen-ai.com/" rel="nofollow">https://keen-ai.com/</a></p>
]]></description><pubDate>Thu, 19 Mar 2026 19:09:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=47444350</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=47444350</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47444350</guid></item><item><title><![CDATA[New comment by petargyurov in "LoGeR – 3D reconstruction from extremely long videos (DeepMind, UC Berkeley)"]]></title><description><![CDATA[
<p>It's easy but it's not cheap. Well, price is relative but capturing video is certainly cheaper.<p>Also, I am not sure how heavy LIDAR units are, but remember that the heavier the payload the more the flight time is reduced. Some drones can only have a single payload, so if you also want to capture (high-res) video/imgs you need to fly again.<p>It all depends on the use-case.</p>
]]></description><pubDate>Tue, 10 Mar 2026 09:12:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=47320786</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=47320786</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47320786</guid></item><item><title><![CDATA[New comment by petargyurov in "Snow Simulation Toy"]]></title><description><![CDATA[
<p>Love it :)<p>I also rate the author's slogan: "make things, not too much, mostly crap". A reference to Michael Pollan's "eat food, not too much, mostly veg".</p>
]]></description><pubDate>Tue, 27 Jan 2026 13:22:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=46779617</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=46779617</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46779617</guid></item><item><title><![CDATA[New comment by petargyurov in "alpr.watch"]]></title><description><![CDATA[
<p>You aren't the one deciding what is a crime and what isn't.</p>
]]></description><pubDate>Wed, 17 Dec 2025 08:45:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=46299625</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=46299625</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46299625</guid></item><item><title><![CDATA[Show HN: SolarStorm – Visualising space weather effects on the power grid]]></title><description><![CDATA[
<p>Hi HN,<p>I wanted to share my team's side project! We like to do R&D projects and investigate new areas, interesting problems, etc.<p>This application visualises the dynamic interplay between space weather and our terrestrial power grid, focusing on Geomagnetically Induced Currents (GICs) across the UK.<p>By visualising the magnetic field, induced electric field, and resulting GICs, users can identify vulnerable areas of the UK power network and assess the potential for operational disruptions during geomagnetic storms.<p>We would love to get some feedback and expand this to cover more power grids in more countries.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46216596">https://news.ycombinator.com/item?id=46216596</a></p>
<p>Points: 5</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 10 Dec 2025 11:34:57 +0000</pubDate><link>https://solarstorm.space/</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=46216596</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46216596</guid></item><item><title><![CDATA[New comment by petargyurov in "When Soviet-made cars roamed Singapore roads"]]></title><description><![CDATA[
<p>I too have fond memories of my dad driving me around in our navy blue Lada. Not sure what the model was, but it was the one with rectangular headlights, not round.
The chassis on that thing was solid metal.<p>I remember one time when I was in the back and my dad took a rather sharp turn at a major junction and the rear door swung open. I calmly alerted him to the situation and with one hand on the steering wheel and one hand reaching behind, somehow got the door closed whilst I sat semi-afraid for my life.<p>I remember the horn also broke so he rewired it to a custom red button that he mounted on the driver's door handle.</p>
]]></description><pubDate>Tue, 11 Nov 2025 07:46:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=45885015</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=45885015</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45885015</guid></item><item><title><![CDATA[New comment by petargyurov in "Show HN: DeepFake – Free AI Face Swap Online"]]></title><description><![CDATA[
<p>No privacy policy.<p>No terms and conditions.<p>No thanks.<p>And that's on top of the already questionable product.</p>
]]></description><pubDate>Mon, 03 Nov 2025 09:30:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=45797307</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=45797307</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45797307</guid></item><item><title><![CDATA[New comment by petargyurov in "Show HN: Hank – Simplest CLI tool to get errors in plain English"]]></title><description><![CDATA[
<p>Looks nice. Would be way more convenient to use if I could just do `?` in the command line after a failed command. I suppose one could create an alias.<p>Regarding your README, I would add a text version of the example in the demo.</p>
]]></description><pubDate>Mon, 20 Oct 2025 13:50:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=45643927</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=45643927</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45643927</guid></item><item><title><![CDATA[New comment by petargyurov in "Towards a Physics Foundation Model"]]></title><description><![CDATA[
<p>Anyone remember that one time, a year or so ago, when some company teased a physics based generative model which showcased a drop of water sliding down a beer bottle and the model could display the forces acting on it?<p>Whatever happened to that? Vapourware?</p>
]]></description><pubDate>Thu, 18 Sep 2025 07:12:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=45286516</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=45286516</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45286516</guid></item><item><title><![CDATA[New comment by petargyurov in "Does anyone think the current AI approach will hit a dead end?"]]></title><description><![CDATA[
<p>I think it already has.<p>We'll get more incremental updates and nice features:<p>* more context size<p>* less hallucinations<p>* more prompt control (or the illusion of)<p>But we won't get AGI this way.<p>From the very beginning LLMs were shown to be incapable of synthesising new ideas. They don't sit there and think; they can only connect dots within a paradigm that we give them. You may give me examples of AI discovering new medicines and math proofs as a counter-argument but I see that as re-enforcing the above.<p>Paired with data and computional scaling issues, I just don't see it happening. They will remain a useful tool, but won't become AGI.<p>And whether they stay affordable is a question of time; all the big players are burning mountains of cash just to edge out the competition in terms of adoption.<p>Is there a level of adoption that can justify the current costs to run these things?</p>
]]></description><pubDate>Mon, 08 Sep 2025 08:48:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=45166006</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=45166006</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45166006</guid></item><item><title><![CDATA[New comment by petargyurov in "Will Smith's concert crowds are real, but AI is blurring the lines"]]></title><description><![CDATA[
<p>On this episode of "Trying to make AI useful"...<p>Seriously, who's idea was this? It can't be a money saving feature; surely it costs more to upscale all these videos than to just host the HD version.<p>And even if you argue it can be used only on low res videos to provide a "better experience", the resulting distortion of reality should be very concerning.</p>
]]></description><pubDate>Tue, 26 Aug 2025 08:23:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=45023789</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=45023789</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45023789</guid></item><item><title><![CDATA[New comment by petargyurov in "Word Chains"]]></title><description><![CDATA[
<p>Yeah I think you're right. You can see it early on that there's just too many connections to make sense of it easily.<p>I wonder if 3D clustering would allow for more space.</p>
]]></description><pubDate>Fri, 08 Aug 2025 19:10:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=44840571</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=44840571</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44840571</guid></item><item><title><![CDATA[Word Chains]]></title><description><![CDATA[
<p>Article URL: <a href="https://petargyurov.com/2025-06-22/word-chains">https://petargyurov.com/2025-06-22/word-chains</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44839684">https://news.ycombinator.com/item?id=44839684</a></p>
<p>Points: 2</p>
<p># Comments: 2</p>
]]></description><pubDate>Fri, 08 Aug 2025 17:45:40 +0000</pubDate><link>https://petargyurov.com/2025-06-22/word-chains</link><dc:creator>petargyurov</dc:creator><comments>https://news.ycombinator.com/item?id=44839684</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44839684</guid></item></channel></rss>