<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: lafalce</title><link>https://news.ycombinator.com/user?id=lafalce</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 11 Oct 2026 06:06:32 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=lafalce" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by lafalce in "Triple-A Minesweeper"]]></title><description><![CDATA[
<p>I need to sweep these mines!</p>
]]></description><pubDate>Fri, 09 Oct 2026 21:10:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=50026591</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=50026591</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50026591</guid></item><item><title><![CDATA[Show HN: Cinematic Grade, a real-time GLSL color grade for the Cinnamon desktop]]></title><description><![CDATA[
<p>Hey guys! I made a screen filter for the computer with the Iron aesthetic, because I really love what it conveys. I was already using my screen in black and white day to day, and I tweaked it a bit so it sits closer to the Iron look without draining the battery in the process<p>github.com/mateolafalce/iron-within<p>I sent this applet to Linux Mint's official Cinnamon Spices repo, so maybe someday it can be downloaded straight from that store: github.com/linuxmint/cinnamon-spices-applets/pull/9088<p>Just that, take care, and I hope you lock in this weekend that's about to start!!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49938827">https://news.ycombinator.com/item?id=49938827</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 02 Oct 2026 21:30:19 +0000</pubDate><link>https://github.com/mateolafalce/iron-within</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=49938827</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49938827</guid></item><item><title><![CDATA[I Built a System One Model on a RTX 3070]]></title><description><![CDATA[
<p>Article URL: <a href="https://twitter.com/lafalcemateo/status/2101414901365248059">https://twitter.com/lafalcemateo/status/2101414901365248059</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49770066">https://news.ycombinator.com/item?id=49770066</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 19 Sep 2026 20:57:12 +0000</pubDate><link>https://twitter.com/lafalcemateo/status/2101414901365248059</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=49770066</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49770066</guid></item><item><title><![CDATA[Paying for Cached Tokens Sucks]]></title><description><![CDATA[
<p>Article URL: <a href="https://twitter.com/lafalcemateo/status/2092061073750782139">https://twitter.com/lafalcemateo/status/2092061073750782139</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49428037">https://news.ycombinator.com/item?id=49428037</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 25 Aug 2026 01:28:06 +0000</pubDate><link>https://twitter.com/lafalcemateo/status/2092061073750782139</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=49428037</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49428037</guid></item><item><title><![CDATA[New comment by lafalce in "Ask HN: What are you working on? (August 2026)"]]></title><description><![CDATA[
<p>I'm working on an open source project to make drone delivery accessible across any industry not only the software, but also the drone hardware</p>
]]></description><pubDate>Sun, 09 Aug 2026 18:15:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=49233973</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=49233973</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49233973</guid></item><item><title><![CDATA[There is no way to know if an LLM API is manipulating you]]></title><description><![CDATA[
<p>Article URL: <a href="https://twitter.com/lafalcemateo/status/2082250304330809738">https://twitter.com/lafalcemateo/status/2082250304330809738</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49103230">https://news.ycombinator.com/item?id=49103230</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 29 Jul 2026 21:19:13 +0000</pubDate><link>https://twitter.com/lafalcemateo/status/2082250304330809738</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=49103230</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49103230</guid></item><item><title><![CDATA[New comment by lafalce in "Someone Build a OS for Claude Code"]]></title><description><![CDATA[
<p>Basically — to get AI-generated Hacker News comments with em dashes :)</p>
]]></description><pubDate>Tue, 23 Jun 2026 00:22:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=48638476</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=48638476</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48638476</guid></item><item><title><![CDATA[Someone Build a OS for Claude Code]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/mateolafalce/claudios/blob/main/README.md">https://github.com/mateolafalce/claudios/blob/main/README.md</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48621576">https://news.ycombinator.com/item?id=48621576</a></p>
<p>Points: 2</p>
<p># Comments: 2</p>
]]></description><pubDate>Sun, 21 Jun 2026 18:58:37 +0000</pubDate><link>https://github.com/mateolafalce/claudios/blob/main/README.md</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=48621576</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48621576</guid></item><item><title><![CDATA[Benchmark Comparison: JSONL vs. TOON output for JSON-render efficiency]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/vercel-labs/json-render/issues/33">https://github.com/vercel-labs/json-render/issues/33</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46706853">https://news.ycombinator.com/item?id=46706853</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 21 Jan 2026 15:17:12 +0000</pubDate><link>https://github.com/vercel-labs/json-render/issues/33</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=46706853</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46706853</guid></item><item><title><![CDATA[I Cut Vercel's JSON-Render LLM Costs by 89% Using Toon]]></title><description><![CDATA[
<p>Article URL: <a href="https://mateolafalce.github.io/2026/I%20Cut%20Vercel%27s%20json-render%20LLM%20Costs%20by%2089%25%20Using%20TOON/ICutVercelsjsonrenderLLMCostsby89UsingTOON.html">https://mateolafalce.github.io/2026/I%20Cut%20Vercel%27s%20json-render%20LLM%20Costs%20by%2089%25%20Using%20TOON/ICutVercelsjsonrenderLLMCostsby89UsingTOON.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46658248">https://news.ycombinator.com/item?id=46658248</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 17 Jan 2026 14:17:22 +0000</pubDate><link>https://mateolafalce.github.io/2026/I%20Cut%20Vercel%27s%20json-render%20LLM%20Costs%20by%2089%25%20Using%20TOON/ICutVercelsjsonrenderLLMCostsby89UsingTOON.html</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=46658248</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46658248</guid></item><item><title><![CDATA[Show HN: Recursive Language Model for Querying Human Action by Ludwig von Mises]]></title><description><![CDATA[
<p>Human Action by Ludwig von Mises is a 900+ page treatise on economics and praxeology dense, complex, and foundational to Austrian economics.<p>I built this tool using Recursive Language Models (RLM) that ingests the entire book and lets you query it conversationally. It downloads the full text from mises.org, processes it with RLM for deep contextual understanding, and serves a simple Flask frontend. Perfect for students, researchers, or anyone curious about Mises's ideas!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46645564">https://news.ycombinator.com/item?id=46645564</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 16 Jan 2026 11:56:23 +0000</pubDate><link>https://github.com/mateolafalce/human-action-rlm</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=46645564</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46645564</guid></item><item><title><![CDATA[Topic2Manim Now Has a UI]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/mateolafalce/topic2manim">https://github.com/mateolafalce/topic2manim</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46606155">https://news.ycombinator.com/item?id=46606155</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 13 Jan 2026 19:09:27 +0000</pubDate><link>https://github.com/mateolafalce/topic2manim</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=46606155</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46606155</guid></item><item><title><![CDATA[Show HN: Turn any topic into a 3Blue1Brown-style video]]></title><description><![CDATA[
<p>Hey HN! I built Topic2Manim to automate the creation of educational videos 
like those from 3Blue1Brown.<p>The workflow is simple:<p>1. Give it any topic (e.g., "how ChatGPT works")<p>2. An LLM generates an educational script divided into scenes<p>3. LLM generates Manim code for each scene<p>4. FFmpeg concatenates everything into a final video<p>Currently working on TTS integration for narration!<p>Would love feedback on the approach and ideas for the TTS integration</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46561801">https://news.ycombinator.com/item?id=46561801</a></p>
<p>Points: 5</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 10 Jan 2026 01:35:53 +0000</pubDate><link>https://github.com/mateolafalce/topic2manim</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=46561801</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46561801</guid></item><item><title><![CDATA[The Engine of Computer Vision]]></title><description><![CDATA[
<p>Article URL: <a href="https://mateolafalce.github.io/2026/The%20Engine%20of%20Computer%20Vision/TheEngineofComputerVision.html">https://mateolafalce.github.io/2026/The%20Engine%20of%20Computer%20Vision/TheEngineofComputerVision.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46530841">https://news.ycombinator.com/item?id=46530841</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 07 Jan 2026 18:57:44 +0000</pubDate><link>https://mateolafalce.github.io/2026/The%20Engine%20of%20Computer%20Vision/TheEngineofComputerVision.html</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=46530841</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46530841</guid></item><item><title><![CDATA[Stop Using Softmax for Everything]]></title><description><![CDATA[
<p>Article URL: <a href="https://mateolafalce.github.io/2026/The%20One%20Cake%20Fallacy%20%28Softmax%20vs.%20Sigmoid%29/TheOneCakeFallacy_Softmaxvs.Sigmoid_.html">https://mateolafalce.github.io/2026/The%20One%20Cake%20Fallacy%20%28Softmax%20vs.%20Sigmoid%29/TheOneCakeFallacy_Softmaxvs.Sigmoid_.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46482357">https://news.ycombinator.com/item?id=46482357</a></p>
<p>Points: 4</p>
<p># Comments: 1</p>
]]></description><pubDate>Sat, 03 Jan 2026 22:25:09 +0000</pubDate><link>https://mateolafalce.github.io/2026/The%20One%20Cake%20Fallacy%20%28Softmax%20vs.%20Sigmoid%29/TheOneCakeFallacy_Softmaxvs.Sigmoid_.html</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=46482357</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46482357</guid></item><item><title><![CDATA[Logistic Regression, the Sigmoid, and Log Loss]]></title><description><![CDATA[
<p>Article URL: <a href="https://mateolafalce.github.io/2026/Logistic%20Regression%2C%20the%20Sigmoid%2C%20and%20Log%20Loss/LogisticRegressiontheSigmoidandLogLoss.html">https://mateolafalce.github.io/2026/Logistic%20Regression%2C%20the%20Sigmoid%2C%20and%20Log%20Loss/LogisticRegressiontheSigmoidandLogLoss.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46472162">https://news.ycombinator.com/item?id=46472162</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 03 Jan 2026 02:26:14 +0000</pubDate><link>https://mateolafalce.github.io/2026/Logistic%20Regression%2C%20the%20Sigmoid%2C%20and%20Log%20Loss/LogisticRegressiontheSigmoidandLogLoss.html</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=46472162</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46472162</guid></item><item><title><![CDATA[Decision Trees vs. Boosting: The One Expert vs. the Committee]]></title><description><![CDATA[
<p>Article URL: <a href="https://mateolafalce.github.io/2026/Decision%20Trees%20vs.%20Boosting_%20The%20One%20Expert%20vs.%20The%20Committee/DecisionTreesvs.BoostingTheOneExpertvs.TheCom.html">https://mateolafalce.github.io/2026/Decision%20Trees%20vs.%20Boosting_%20The%20One%20Expert%20vs.%20The%20Committee/DecisionTreesvs.BoostingTheOneExpertvs.TheCom.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46455819">https://news.ycombinator.com/item?id=46455819</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 01 Jan 2026 17:12:54 +0000</pubDate><link>https://mateolafalce.github.io/2026/Decision%20Trees%20vs.%20Boosting_%20The%20One%20Expert%20vs.%20The%20Committee/DecisionTreesvs.BoostingTheOneExpertvs.TheCom.html</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=46455819</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46455819</guid></item><item><title><![CDATA[Understanding Decision Trees: The White Box of Machine Learning]]></title><description><![CDATA[
<p>Article URL: <a href="https://mateolafalce.github.io/2025/Understanding%20Decision%20Trees_%20The%20White%20Box%20of%20Machine%20Learning/UnderstandingDecisionTreesTheWhiteBoxofMachin.html">https://mateolafalce.github.io/2025/Understanding%20Decision%20Trees_%20The%20White%20Box%20of%20Machine%20Learning/UnderstandingDecisionTreesTheWhiteBoxofMachin.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46447955">https://news.ycombinator.com/item?id=46447955</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 31 Dec 2025 20:29:27 +0000</pubDate><link>https://mateolafalce.github.io/2025/Understanding%20Decision%20Trees_%20The%20White%20Box%20of%20Machine%20Learning/UnderstandingDecisionTreesTheWhiteBoxofMachin.html</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=46447955</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46447955</guid></item><item><title><![CDATA[The Comprehensive Cognition Blog]]></title><description><![CDATA[
<p>Article URL: <a href="https://mateolafalce.github.io/">https://mateolafalce.github.io/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46359186">https://news.ycombinator.com/item?id=46359186</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 22 Dec 2025 21:15:33 +0000</pubDate><link>https://mateolafalce.github.io/</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=46359186</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46359186</guid></item><item><title><![CDATA[I Cloned Myself with a Markov Chain]]></title><description><![CDATA[
<p>Article URL: <a href="https://mateolafalce.github.io/2025/I%20Cloned%20Myself%20with%20a%20Markov%20Chain/IClonedMyselfwithaMarkovChain.html">https://mateolafalce.github.io/2025/I%20Cloned%20Myself%20with%20a%20Markov%20Chain/IClonedMyselfwithaMarkovChain.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46328862">https://news.ycombinator.com/item?id=46328862</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 19 Dec 2025 18:03:53 +0000</pubDate><link>https://mateolafalce.github.io/2025/I%20Cloned%20Myself%20with%20a%20Markov%20Chain/IClonedMyselfwithaMarkovChain.html</link><dc:creator>lafalce</dc:creator><comments>https://news.ycombinator.com/item?id=46328862</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46328862</guid></item></channel></rss>