<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: ZeljkoS</title><link>https://news.ycombinator.com/user?id=ZeljkoS</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 22 Nov 2026 03:14:21 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=ZeljkoS" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[The gas pipeline where Ukraine is fighting an underground war with Russia]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.bbc.com/news/videos/c8p3vw4q6nzzo">https://www.bbc.com/news/videos/c8p3vw4q6nzzo</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50557854">https://news.ycombinator.com/item?id=50557854</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 19 Nov 2026 09:24:58 +0000</pubDate><link>https://www.bbc.com/news/videos/c8p3vw4q6nzzo</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=50557854</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50557854</guid></item><item><title><![CDATA[Claudia.gallery]]></title><description><![CDATA[
<p>Article URL: <a href="https://claudia.gallery/">https://claudia.gallery/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50464745">https://news.ycombinator.com/item?id=50464745</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 12 Nov 2026 09:01:26 +0000</pubDate><link>https://claudia.gallery/</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=50464745</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50464745</guid></item><item><title><![CDATA[Goodyear Inflatoplane]]></title><description><![CDATA[
<p>Article URL: <a href="https://en.wikipedia.org/wiki/Goodyear_Inflatoplane">https://en.wikipedia.org/wiki/Goodyear_Inflatoplane</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50440352">https://news.ycombinator.com/item?id=50440352</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 10 Nov 2026 13:51:27 +0000</pubDate><link>https://en.wikipedia.org/wiki/Goodyear_Inflatoplane</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=50440352</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50440352</guid></item><item><title><![CDATA[Building a multiplayer game world with autonomous Fable-class models]]></title><description><![CDATA[
<p>Article URL: <a href="https://simonwillison.net/2026/Oct/29/how-i-built-the-most-ai-pilled-company-in-the-world/">https://simonwillison.net/2026/Oct/29/how-i-built-the-most-ai-pilled-company-in-the-world/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50303018">https://news.ycombinator.com/item?id=50303018</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 30 Oct 2026 12:31:15 +0000</pubDate><link>https://simonwillison.net/2026/Oct/29/how-i-built-the-most-ai-pilled-company-in-the-world/</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=50303018</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50303018</guid></item><item><title><![CDATA[What we know so far about Spain train crash]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.bbc.com/news/articles/cm8xz7pkd0jjo">https://www.bbc.com/news/articles/cm8xz7pkd0jjo</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50286197">https://news.ycombinator.com/item?id=50286197</a></p>
<p>Points: 244</p>
<p># Comments: 453</p>
]]></description><pubDate>Thu, 29 Oct 2026 08:55:08 +0000</pubDate><link>https://www.bbc.com/news/articles/cm8xz7pkd0jjo</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=50286197</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50286197</guid></item><item><title><![CDATA[New comment by ZeljkoS in "The Mathocalypse"]]></title><description><![CDATA[
<p>To me, the real lead of the article is buried here:<p>> apparently they tried the model on about 8,000 problems. So, right now it “merely” solves ~5% of the longstanding open mathematical problems that it’s asked about, the problems that whole communities have spent years on, after a single 3-hour attempt on them.<p>Back-of-the-envelope cost calculation:<p>3 hours of GPT-Pro compute per attempt / 5% success rate → <i>60 hours of compute per solved open math problem</i><p>At GPT-6 Astra API long-context pricing ($75/M output tokens), assuming 50 reasoning tokens/s, that's roughly <i>$810 per solution</i>:<p>60 h × 3,600 s × 50 tokens/s × $75 / 1,000,000 = $810<p>Of course, actual token usage is unknown. But even if off by 10x, $8100 is cheap for solving a longstanding mathematical problem.</p>
]]></description><pubDate>Thu, 08 Oct 2026 10:46:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=50004205</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=50004205</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50004205</guid></item><item><title><![CDATA[One's Vibe – discover AI-built products you can try]]></title><description><![CDATA[
<p>Article URL: <a href="https://onesvibe.app">https://onesvibe.app</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50003157">https://news.ycombinator.com/item?id=50003157</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 08 Oct 2026 08:16:58 +0000</pubDate><link>https://onesvibe.app</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=50003157</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50003157</guid></item><item><title><![CDATA[Claude OF DUTY – a browser FPS with no art assets]]></title><description><![CDATA[
<p>Article URL: <a href="https://claude-of-duty.com/">https://claude-of-duty.com/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50002780">https://news.ycombinator.com/item?id=50002780</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 08 Oct 2026 07:20:54 +0000</pubDate><link>https://claude-of-duty.com/</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=50002780</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50002780</guid></item><item><title><![CDATA[Urbanloop – Green Transport – Smart Sustainable Mobility]]></title><description><![CDATA[
<p>Article URL: <a href="https://urbanloop.fr/en/">https://urbanloop.fr/en/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49906017">https://news.ycombinator.com/item?id=49906017</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 30 Sep 2026 08:30:03 +0000</pubDate><link>https://urbanloop.fr/en/</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=49906017</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49906017</guid></item><item><title><![CDATA[WorldCrafter: Consistent Video World Model with Implicit 3D-Aware Memory]]></title><description><![CDATA[
<p>Article URL: <a href="https://drexubery.github.io/WorldCrafter/">https://drexubery.github.io/WorldCrafter/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49884125">https://news.ycombinator.com/item?id=49884125</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 28 Sep 2026 20:47:42 +0000</pubDate><link>https://drexubery.github.io/WorldCrafter/</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=49884125</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49884125</guid></item><item><title><![CDATA[The Future of AI: Five Possible Scenarios – Centre for Future Generations]]></title><description><![CDATA[
<p>Article URL: <a href="https://cfg.eu/advanced-ai-possible-futures/">https://cfg.eu/advanced-ai-possible-futures/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49879930">https://news.ycombinator.com/item?id=49879930</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 28 Sep 2026 15:48:39 +0000</pubDate><link>https://cfg.eu/advanced-ai-possible-futures/</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=49879930</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49879930</guid></item><item><title><![CDATA[Rope Splicing]]></title><description><![CDATA[
<p>Article URL: <a href="https://en.wikipedia.org/wiki/Rope_splicing">https://en.wikipedia.org/wiki/Rope_splicing</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49717339">https://news.ycombinator.com/item?id=49717339</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 15 Sep 2026 19:11:04 +0000</pubDate><link>https://en.wikipedia.org/wiki/Rope_splicing</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=49717339</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49717339</guid></item><item><title><![CDATA[New comment by ZeljkoS in "Vals.ai Benchmark – International Olympiad in Informatics"]]></title><description><![CDATA[
<p>"The two leaders score 100% on 2026 even though the contest ran after their training cutoffs, so recency alone does not cap performance."</p>
]]></description><pubDate>Sat, 12 Sep 2026 15:05:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=49673061</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=49673061</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49673061</guid></item><item><title><![CDATA[Vals.ai Benchmark – International Olympiad in Informatics]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.vals.ai/benchmarks/ioi">https://www.vals.ai/benchmarks/ioi</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49673057">https://news.ycombinator.com/item?id=49673057</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Sat, 12 Sep 2026 15:05:04 +0000</pubDate><link>https://www.vals.ai/benchmarks/ioi</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=49673057</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49673057</guid></item><item><title><![CDATA[Founder of Chinese property giant Evergrande sentenced to life in prison]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.bbc.com/news/articles/cd0x9mjjmgjo">https://www.bbc.com/news/articles/cd0x9mjjmgjo</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49372151">https://news.ycombinator.com/item?id=49372151</a></p>
<p>Points: 19</p>
<p># Comments: 3</p>
]]></description><pubDate>Thu, 20 Aug 2026 09:02:11 +0000</pubDate><link>https://www.bbc.com/news/articles/cd0x9mjjmgjo</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=49372151</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49372151</guid></item><item><title><![CDATA[TamedTable – AI ETL in Natural Language]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.tamedtable.com/">https://www.tamedtable.com/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49335191">https://news.ycombinator.com/item?id=49335191</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 17 Aug 2026 18:07:59 +0000</pubDate><link>https://www.tamedtable.com/</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=49335191</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49335191</guid></item><item><title><![CDATA[Ferrari's Controversial Luce EV Has Reportedly Sold Out]]></title><description><![CDATA[
<p>Article URL: <a href="https://robbreport.com/motors/cars/ferrari-luce-2026-production-run-sold-out-1238515555/">https://robbreport.com/motors/cars/ferrari-luce-2026-production-run-sold-out-1238515555/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49180173">https://news.ycombinator.com/item?id=49180173</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Wed, 05 Aug 2026 08:42:43 +0000</pubDate><link>https://robbreport.com/motors/cars/ferrari-luce-2026-production-run-sold-out-1238515555/</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=49180173</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49180173</guid></item><item><title><![CDATA[New comment by ZeljkoS in "Show HN: TamedTable, AI ETL in Natural Language"]]></title><description><![CDATA[
<p>Great!<p>If <i>all</i> plan queries are deterministic, the "Save recipe as Python" action saves the entire process as a deterministic script:<p><a href="https://www.tamedtable.com/#save-py" rel="nofollow">https://www.tamedtable.com/#save-py</a><p>Honestly, you are probably not the target user, as you seem familiar with data cleanup scripts and AI agents. I think the target users would be:<p>A) Non-technical people in your org who clean data by hand because they don't know to automate it.<p>B) Technical people who want to test multiple queries and preview transformations before generating an AI-driven transformation flow (and are OK with it).</p>
]]></description><pubDate>Sun, 02 Aug 2026 10:30:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=49143084</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=49143084</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49143084</guid></item><item><title><![CDATA[New comment by ZeljkoS in "Show HN: TamedTable, AI ETL in Natural Language"]]></title><description><![CDATA[
<p>But, it writes an execution plan :) Example here:<p><a href="https://github.com/ZSvedic/TamedTable/blob/main/spec/test-cases/cleanup.flow" rel="nofollow">https://github.com/ZSvedic/TamedTable/blob/main/spec/test-ca...</a><p>And if an action can be done deterministically, then JS code will be generated:<p><a href="https://github.com/ZSvedic/TamedTable/blob/main/spec/test-cases/sort-sql.flow" rel="nofollow">https://github.com/ZSvedic/TamedTable/blob/main/spec/test-ca...</a><p>If data cleanup needs to be deterministic, why is so much of it done by humans? Two humans also won't normalize the same table in the same way. The main thesis is that AI data cleanup is cheaper and less mistake-prone than the same work done by a bored intern.</p>
]]></description><pubDate>Sun, 02 Aug 2026 08:25:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=49142290</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=49142290</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49142290</guid></item><item><title><![CDATA[Show HN: TamedTable, AI ETL in Natural Language]]></title><description><![CDATA[
<p>Hi HN, TamedTable is an LLM harness for data ETL.<p>And yes, it was developed using AI, meaning you can take the entire specification and recreate it to your desires:<p><a href="https://github.com/ZSvedic/TamedTable" rel="nofollow">https://github.com/ZSvedic/TamedTable</a></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49142102">https://news.ycombinator.com/item?id=49142102</a></p>
<p>Points: 9</p>
<p># Comments: 4</p>
]]></description><pubDate>Sun, 02 Aug 2026 07:51:37 +0000</pubDate><link>https://www.tamedtable.com/</link><dc:creator>ZeljkoS</dc:creator><comments>https://news.ycombinator.com/item?id=49142102</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49142102</guid></item></channel></rss>