<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: michaeld123</title><link>https://news.ycombinator.com/user?id=michaeld123</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 27 Jun 2026 04:54:10 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=michaeld123" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by michaeld123 in "Ask HN: Who wants to be hired? (May 2026)"]]></title><description><![CDATA[
<p><p><pre><code>  Location: Takoma Park, MD, USA
  Remote: Yes
  Willing to relocate: No
  Technologies: All LLMs, Python, JavaScript, TypeScript, Swift 
  Portfolio: https://www.michaeldouma.com
  Email: m5@inotherwords-studio.com
</code></pre>
I help make performant systems easy to use, both the first time and the 1000th.
Last year I built Linguabase, a semantic graph of 400K terms and 63M relationships from 130M LLM inferences. I work across the stack, from systems architecture to highly usable design, and I've led cross-functional teams of 9 to 40. Currently an AI Engineer at the U.S. Treasury. Previously ran a word-game studio funded by a $295K NSF SBIR. Earlier work includes SpicyNodes (40M users), ProstateCalculator (neural-net health AI, 1.5M patients), and time.gov. I judge games for IGF, MAGFest, CODiE, and GEE.<p>I'm good at communicating clearly: my interactive article on multi-word expressions in English trended on Hacker News in February.<p>Looking for an applied AI role at a smaller company where I can help you strategize, build, and deploy. I'd shine on developer tools, learning platforms, knowledge products, creative AI, thinky games, or anything that needs to be more accessible to users.<p><pre><code>  Latest: https://www.linguabase.org, https://www.inotherwords.app
  LinkedIn: https://www.linkedin.com/in/michaeldouma/</code></pre></p>
]]></description><pubDate>Sat, 02 May 2026 17:33:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=47988512</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47988512</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47988512</guid></item><item><title><![CDATA[New comment by michaeld123 in "Ask HN: Who wants to be hired? (April 2026)"]]></title><description><![CDATA[
<p><p><pre><code>  Location: Takoma Park, MD, USA
  Remote: Yes
  Willing to relocate: No
  Technologies: Python, LLM pipeline orchestration (130M+ API calls across Claude/GPT/Grok), JavaScript
  Portfolio: https://www.michaeldouma.com
  Email: m5@inotherwords-studio.com
</code></pre>
My interactive article on multi-word expressions in English trended #1 on Hacker News in March. I help make systems easy to use, both the first time and the 1000th.<p>Currently at the U.S. Treasury as an AI specialist, but I want to get back to a smaller team. I've led cross-functional teams of 9 to 40. Last year, I launched Linguabase, a semantic graph of 400K terms and 63M relationships from 130M LLM inferences. Before that, I ran a word-game studio funded by a $295K NSF SBIR. Past work includes SpicyNodes (40M users), ProstateCalculator (neural-net health AI, 1.5M patients), and time.gov. I judge games for IGF, MAGFest, CODiE, and GEE.<p>Looking for an applied AI role at a smaller company where I can build. Developer tools, learning platforms, knowledge products, creative AI, brain health. Anywhere the core problem is some version of 'this is powerful but nobody can figure it out.'<p><pre><code>  Latest: https://www.inotherwords.app
  LinkedIn: https://www.linkedin.com/in/michaeldouma/</code></pre></p>
]]></description><pubDate>Thu, 02 Apr 2026 17:10:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=47617168</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47617168</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47617168</guid></item><item><title><![CDATA[New comment by michaeld123 in "Show HN: Antimatter – Match the opposites (Mahjong solitaire mechanic)"]]></title><description><![CDATA[
<p>Both your points are solid. I think I'm pretty liberal about opposites, I can see opposites to major political and cultural figures too.  You are right that the mahjong presentation loses rigor if there's not enough downside from choosing the wrong sequence. The mobile mahjong games often have a small fill-tray so the player needs to really focus on the sequence.</p>
]]></description><pubDate>Wed, 25 Mar 2026 00:17:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=47511500</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47511500</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47511500</guid></item><item><title><![CDATA[New comment by michaeld123 in "Show HN: Antimatter – Match the opposites (Mahjong solitaire mechanic)"]]></title><description><![CDATA[
<p>the older generation of vectors, like word2vec, compress to one sense of a word, but even if we ignore polysemy, opposites have a lot in common. So for any antonym pair, they would not be minus-1, they would be actually pretty close.<p>The big challenge is when we go beyond antonyms with clear scales like heat, speed, size. To me "as of now" is recent, and therefore opposite to "old". I would like a word other than "opposite" or "antonym" or "contrast" that captures a wider range.</p>
]]></description><pubDate>Wed, 25 Mar 2026 00:15:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=47511476</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47511476</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47511476</guid></item><item><title><![CDATA[Show HN: Antimatter – Match the opposites (Mahjong solitaire mechanic)]]></title><description><![CDATA[
<p>I love word association games. Here's a playable wordplay game where you match opposite word tiles. After playtesting a lot of mechanics, I think opposites play really nicely with Mahjong solitaire.<p>The current generation of frontier LLMs can't make puzzles that get much more interesting than hot-vs-big-vs-fast. New inferences keep circling a small pool of concepts unless the prompting has a way to get the LLM into new territories of language. Puzzlemaking needs graph traversals.<p>I made 20 levels algorithmically because I work with a huge semantic graph with over 100M edges, built from manual lexicography and millions of LLM inferences (various models). I keep exploring what can emerge from this graph. The puzzles are randomly selected; reload to see others.<p>The front-end was built with Claude Code.<p>Maybe someday I'll make this into a mobile game, increase the complexity and peril. If you are a gamedev, feel free to dissect it and borrow any parts.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47507856">https://news.ycombinator.com/item?id=47507856</a></p>
<p>Points: 12</p>
<p># Comments: 5</p>
]]></description><pubDate>Tue, 24 Mar 2026 19:32:32 +0000</pubDate><link>https://www.linguabase.org/antimatter/</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47507856</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47507856</guid></item><item><title><![CDATA[New comment by michaeld123 in "The New York Times hated crossword puzzles before it embraced them"]]></title><description><![CDATA[
<p>Historical look back at old articles on this popular word game. 
February 15, 2022 - bigthink.com
Long before the Wordle mania, there was the crossword puzzle craze. And newspapers around the world condemned them as an “invasive weed” that caused mental illnesses and even murder.</p>
]]></description><pubDate>Thu, 12 Mar 2026 01:45:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=47345240</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47345240</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47345240</guid></item><item><title><![CDATA[The New York Times hated crossword puzzles before it embraced them]]></title><description><![CDATA[
<p>Article URL: <a href="https://bigthink.com/pessimists-archive/new-york-times-hated-crossword-puzzles-wordle/">https://bigthink.com/pessimists-archive/new-york-times-hated-crossword-puzzles-wordle/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47345239">https://news.ycombinator.com/item?id=47345239</a></p>
<p>Points: 4</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 12 Mar 2026 01:45:59 +0000</pubDate><link>https://bigthink.com/pessimists-archive/new-york-times-hated-crossword-puzzles-wordle/</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47345239</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47345239</guid></item><item><title><![CDATA[New comment by michaeld123 in "Ask HN: Who wants to be hired? (March 2026)"]]></title><description><![CDATA[
<p><p><pre><code>  Location: Takoma Park, MD, USA
  Remote: Yes
  Willing to relocate: No
  Technologies: Python, Swift, JavaScript, semantic systems, LLM orchestration
  Portfolio: https://www.michaeldouma.com
  Email: m5@inotherwords-studio.com
</code></pre>
I had an article trending on HN last week about "words with spaces" in English. I can help you make your complicated system be more usable for your consumers.<p>I have a track record that spans from govt services (I created time.gov in 1999), visualizations (SpicyNodes, 40M users), AI-based health info before AI was a thing (ProstateCalculator, 1.5M patients), and association-based word games (two games, plus a game-centric game studio, NSF funded w/ $295K SBIR). I also judge games for several awards (IGF, MagFest, CODiE, GEE, Serious Games).<p>How can I help you? Maybe your project needs an overall product vision, or incremental improvements that help first-time and long-time users know and (enjoy!) using your product.<p>I would love to work with your team in a product/design leadership role, at a smallish-company. I can work with developer tools, learning platforms, knowledge products, brain health, creative AI.<p><pre><code>  Latest: https://www.inotherwords.app
  LinkedIn: https://www.linkedin.com/in/michaeldouma/</code></pre></p>
]]></description><pubDate>Wed, 04 Mar 2026 14:19:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=47247679</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47247679</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47247679</guid></item><item><title><![CDATA[New comment by michaeld123 in "Half million 'Words with Spaces' missing from dictionaries"]]></title><description><![CDATA[
<p>Claude is AI and can make mistakes. Please double-check responses.</p>
]]></description><pubDate>Wed, 25 Feb 2026 18:50:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=47155976</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47155976</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47155976</guid></item><item><title><![CDATA[New comment by michaeld123 in "Half million 'Words with Spaces' missing from dictionaries"]]></title><description><![CDATA[
<p>And I attempted to add your 'svart hull' note.</p>
]]></description><pubDate>Wed, 25 Feb 2026 14:54:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=47152351</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47152351</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47152351</guid></item><item><title><![CDATA[New comment by michaeld123 in "Half million 'Words with Spaces' missing from dictionaries"]]></title><description><![CDATA[
<p>I just adapted your comments into the paragraph starting with "German". Hopefully accurately.</p>
]]></description><pubDate>Wed, 25 Feb 2026 14:51:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=47152303</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47152303</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47152303</guid></item><item><title><![CDATA[New comment by michaeld123 in "Half million 'Words with Spaces' missing from dictionaries"]]></title><description><![CDATA[
<p>My bad. there's a little sidebar about it, but I put it lower after the chart because there wasn't room. You might still not find my logic on the 15% satisfying, but it's there.</p>
]]></description><pubDate>Wed, 25 Feb 2026 14:14:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=47151753</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47151753</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47151753</guid></item><item><title><![CDATA[New comment by michaeld123 in "Half million 'Words with Spaces' missing from dictionaries"]]></title><description><![CDATA[
<p>It's not so much the prompt, as the volume. This overall project has involved >100M LLM inferences, spread across 1.9M headwords. the building block is "what words or short terms are related to X?", but scaled out. Plus a lot of filtering. So it's mostly a reflection of English, and also a reflection of what ChatGPT and Claude report back as a significant collocation.</p>
]]></description><pubDate>Wed, 25 Feb 2026 14:12:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=47151736</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47151736</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47151736</guid></item><item><title><![CDATA[New comment by michaeld123 in "Half million 'Words with Spaces' missing from dictionaries"]]></title><description><![CDATA[
<p>Ha — you're probably right that it would have been less controversial. But I kept it precisely because it's arguable. Added a parenthetical acknowledging the HN debate and framing it as on-the-fence by design</p>
]]></description><pubDate>Wed, 25 Feb 2026 13:31:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=47151238</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47151238</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47151238</guid></item><item><title><![CDATA[New comment by michaeld123 in "Half million 'Words with Spaces' missing from dictionaries"]]></title><description><![CDATA[
<p>Added a note: "'I love you' isn't opaque, but it's tight enough to put on a tile." The familiar end of the spectrum picks up collocations that are transparent but loaded — I'm not claiming they're words in the traditional sense, but they're useful vocabulary for word games, which is where I'm coming from.</p>
]]></description><pubDate>Wed, 25 Feb 2026 13:31:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=47151229</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47151229</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47151229</guid></item><item><title><![CDATA[New comment by michaeld123 in "Half million 'Words with Spaces' missing from dictionaries"]]></title><description><![CDATA[
<p>You were right — it is now. Thanks</p>
]]></description><pubDate>Wed, 25 Feb 2026 13:30:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=47151225</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47151225</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47151225</guid></item><item><title><![CDATA[New comment by michaeld123 in "Half million 'Words with Spaces' missing from dictionaries"]]></title><description><![CDATA[
<p>Yeah — added a note below the slider that the obscure end is noise (LLM artifacts, jargon fragments, Wiktionary debris) and that where to draw the line is up to the reader. It was always intended to show the full gradient including where it breaks down, but that wasn't stated</p>
]]></description><pubDate>Wed, 25 Feb 2026 13:30:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=47151223</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47151223</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47151223</guid></item><item><title><![CDATA[New comment by michaeld123 in "Half million 'Words with Spaces' missing from dictionaries"]]></title><description><![CDATA[
<p>Added Japanese nettō alongside the Slavic examples. Thanks for the specifics</p>
]]></description><pubDate>Wed, 25 Feb 2026 13:29:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=47151215</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47151215</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47151215</guid></item><item><title><![CDATA[New comment by michaeld123 in "Half million 'Words with Spaces' missing from dictionaries"]]></title><description><![CDATA[
<p>This was a great detail — added Russian kipyatok and Polish wrzątok to the article as evidence that "boiling water" carries enough conceptual weight that other languages crystallized it into a single word</p>
]]></description><pubDate>Wed, 25 Feb 2026 13:29:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=47151212</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47151212</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47151212</guid></item><item><title><![CDATA[New comment by michaeld123 in "Half million 'Words with Spaces' missing from dictionaries"]]></title><description><![CDATA[
<p>Added Dutch "creditcard" as another example. Thanks</p>
]]></description><pubDate>Wed, 25 Feb 2026 13:29:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=47151208</link><dc:creator>michaeld123</dc:creator><comments>https://news.ycombinator.com/item?id=47151208</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47151208</guid></item></channel></rss>