<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: tmulc18</title><link>https://news.ycombinator.com/user?id=tmulc18</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 19 Nov 2026 22:03:08 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=tmulc18" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Show HN: Fitness MCP]]></title><description><![CDATA[
<p>There's no external MCP for your fitness (Garmin / Strava) data, so we built one.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47433892">https://news.ycombinator.com/item?id=47433892</a></p>
<p>Points: 7</p>
<p># Comments: 4</p>
]]></description><pubDate>Thu, 19 Mar 2026 02:00:59 +0000</pubDate><link>https://getfast.ai/claude-connector</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=47433892</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47433892</guid></item><item><title><![CDATA[Nano Banana on Gemini is not the same as on AI Studio]]></title><description><![CDATA[
<p>Article URL: <a href="https://twitter.com/MulcChocolate/status/1999574382549827915">https://twitter.com/MulcChocolate/status/1999574382549827915</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46248354">https://news.ycombinator.com/item?id=46248354</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 12 Dec 2025 20:19:07 +0000</pubDate><link>https://twitter.com/MulcChocolate/status/1999574382549827915</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=46248354</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46248354</guid></item><item><title><![CDATA[New comment by tmulc18 in "Ask HN: Who is hiring? (December 2025)"]]></title><description><![CDATA[
<p>GetFast | Founding Engineer | Bay Area / Remote<p>We're on a mission to simplify running through wearables data.  We're a small team of runners who love to build.<p>We're looking for a founding engineer to shape the future of our product and company. You’ll work across the stack–from building reliable, scalable systems to rapidly prototyping and launching new user-facing features. You’ll have significant ownership and influence on architecture, product direction, and engineering culture.<p>Ideally you love a few of the following:
 - Foundation ML models in the sensory space
 - Chat agents
 - Novel data visualizations
 - Recommendation systems
 - Operations research
 - Unique UX<p><a href="https://getfast.ai/jobs" rel="nofollow">https://getfast.ai/jobs</a></p>
]]></description><pubDate>Mon, 01 Dec 2025 18:22:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=46110931</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=46110931</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46110931</guid></item><item><title><![CDATA[New comment by tmulc18 in "Ask HN: What Are You Working On? (Nov 2025)"]]></title><description><![CDATA[
<p><a href="https://getfast.ai/strava/login" rel="nofollow">https://getfast.ai/strava/login</a>
Using transformers to understand fitness data</p>
]]></description><pubDate>Sun, 09 Nov 2025 22:58:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=45870096</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=45870096</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45870096</guid></item><item><title><![CDATA[New comment by tmulc18 in "Race SPT: Sensor Pretrained Transformer"]]></title><description><![CDATA[
<p>We trained a model on sensor data to learn useful patterns for predicting running race performances.</p>
]]></description><pubDate>Thu, 30 Oct 2025 23:15:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=45766534</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=45766534</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45766534</guid></item><item><title><![CDATA[Race SPT: Sensor Pretrained Transformer]]></title><description><![CDATA[
<p>Article URL: <a href="https://getfast.ai/strava/login">https://getfast.ai/strava/login</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45766533">https://news.ycombinator.com/item?id=45766533</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 30 Oct 2025 23:15:44 +0000</pubDate><link>https://getfast.ai/strava/login</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=45766533</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45766533</guid></item><item><title><![CDATA[New comment by tmulc18 in "Everything is correlated (2014–23)"]]></title><description><![CDATA[
<p>gwern is goated</p>
]]></description><pubDate>Fri, 22 Aug 2025 06:49:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=44981658</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=44981658</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44981658</guid></item><item><title><![CDATA[Show HN: Chat with Your Wearables Data]]></title><description><![CDATA[
<p>Article URL: <a href="https://getfast.ai/products/chat">https://getfast.ai/products/chat</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44977592">https://news.ycombinator.com/item?id=44977592</a></p>
<p>Points: 5</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 21 Aug 2025 20:22:36 +0000</pubDate><link>https://getfast.ai/products/chat</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=44977592</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44977592</guid></item><item><title><![CDATA[I stumbled into the effective oxygen percentage by looking at model errors]]></title><description><![CDATA[
<p>Article URL: <a href="https://getfast.ai/blogs/altitude-correction">https://getfast.ai/blogs/altitude-correction</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44678077">https://news.ycombinator.com/item?id=44678077</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 25 Jul 2025 00:34:58 +0000</pubDate><link>https://getfast.ai/blogs/altitude-correction</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=44678077</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44678077</guid></item><item><title><![CDATA[Show HN: I built a tool to show how people trained for your goal marathon time]]></title><description><![CDATA[
<p>The idea for this came from wanting something like Naviance (let’s you see the GPA and test scores of admitted students for a given college) for marathon running.<p>In general, we’re working on making your running data more useful, and our newest tool, called, "Marathon Cohorts," gives you stats about runners who finished a marathon in a given time.  You pick a marathon time / cohort and then look at<p>- Weekly training mileage<p>- Fastest 5k, 10k, half marathon, and 30k during training.<p>You can adjust the cohorts to see how these values change as the marathon time gets slower / faster.<p>If you are logged in and connected with Strava / Garmin, we compute your stats for you and overlay them.  But you can explore anonymously–no login required.<p>There’s also a little shareable image generator we’re experimenting with (to make it easier to share on Strava).<p>It’s free right now, but we’re considering a freemium model — and we’d love thoughts on:<p>- Giving users X free queries (per month) before locking the tool?<p>- What would feel worth paying for?<p>- What other stats do you want to see?<p>- Better name for the tool?<p>Let us know what you think!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44254073">https://news.ycombinator.com/item?id=44254073</a></p>
<p>Points: 6</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 12 Jun 2025 03:34:58 +0000</pubDate><link>https://getfast.ai/cohorts</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=44254073</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44254073</guid></item><item><title><![CDATA[New comment by tmulc18 in "Show HN: MidWord – A Word-Guessing Game"]]></title><description><![CDATA[
<p>Would be more fun (even if you call it "easy mode") if you had the alphabet at the top of the page! Took me 17 tries to get "prepare" but I had a lot of mistakes because I forgot what came after what in the alphabet.</p>
]]></description><pubDate>Wed, 11 Jun 2025 17:25:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=44249803</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=44249803</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44249803</guid></item><item><title><![CDATA[New comment by tmulc18 in "Tensorflow 2.0: models migration and new design"]]></title><description><![CDATA[
<p>2.5 years of learning tensorflow now gone to waste :(</p>
]]></description><pubDate>Tue, 13 Nov 2018 22:57:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=18445700</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=18445700</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=18445700</guid></item><item><title><![CDATA[Vanilla web app for labeling audio files]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/tmulc18/AudioLabeler">https://github.com/tmulc18/AudioLabeler</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=15874583">https://news.ycombinator.com/item?id=15874583</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 07 Dec 2017 21:40:49 +0000</pubDate><link>https://github.com/tmulc18/AudioLabeler</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=15874583</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=15874583</guid></item><item><title><![CDATA[Show HN: Microsoft releases AirSim]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.microsoft.com/en-us/research/blog/autonomous-car-research/">https://www.microsoft.com/en-us/research/blog/autonomous-car-research/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=15752036">https://news.ycombinator.com/item?id=15752036</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 21 Nov 2017 22:04:30 +0000</pubDate><link>https://www.microsoft.com/en-us/research/blog/autonomous-car-research/</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=15752036</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=15752036</guid></item><item><title><![CDATA[Distributed TensorFlow (DTF) Guide]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/tmulc18/Distributed-TensorFlow-Guide">https://github.com/tmulc18/Distributed-TensorFlow-Guide</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=15559827">https://news.ycombinator.com/item?id=15559827</a></p>
<p>Points: 11</p>
<p># Comments: 2</p>
]]></description><pubDate>Thu, 26 Oct 2017 15:35:52 +0000</pubDate><link>https://github.com/tmulc18/Distributed-TensorFlow-Guide</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=15559827</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=15559827</guid></item><item><title><![CDATA[New comment by tmulc18 in "Speech Recognition Is Not Solved"]]></title><description><![CDATA[
<p>In the caption for figure 2 there is this quote, "Notice the humans are worse at transcribing the non-American accents." But when I look at the bar graph, I see the word error rates of the model is much higher than the word error rates of humans for most of the non-American accents.  Am I missing something?</p>
]]></description><pubDate>Tue, 24 Oct 2017 23:46:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=15546181</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=15546181</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=15546181</guid></item><item><title><![CDATA[Deep Voice 3: 2000-Speaker Neural Text-To-Speech]]></title><description><![CDATA[
<p>Article URL: <a href="https://arxiv.org/abs/1710.07654v1">https://arxiv.org/abs/1710.07654v1</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=15542178">https://news.ycombinator.com/item?id=15542178</a></p>
<p>Points: 5</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 24 Oct 2017 15:16:32 +0000</pubDate><link>https://arxiv.org/abs/1710.07654v1</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=15542178</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=15542178</guid></item><item><title><![CDATA[Distributed Deep Learning Reading List]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/tmulc18/DistributedDeepLearningReads">https://github.com/tmulc18/DistributedDeepLearningReads</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=15519541">https://news.ycombinator.com/item?id=15519541</a></p>
<p>Points: 7</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 20 Oct 2017 22:30:05 +0000</pubDate><link>https://github.com/tmulc18/DistributedDeepLearningReads</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=15519541</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=15519541</guid></item><item><title><![CDATA[USPO grants Google a patent on dropout]]></title><description><![CDATA[
<p>Article URL: <a href="http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=%2Fnetahtml%2FPTO%2Fsearch-bool.html&r=1&f=G&l=50&co1=AND&d=PTXT&s1=%22System+method+addressing+overfitting+neural+network%22&OS=">http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=%2Fnetahtml%2FPTO%2Fsearch-bool.html&r=1&f=G&l=50&co1=AND&d=PTXT&s1=%22System+method+addressing+overfitting+neural+network%22&OS=</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=15363552">https://news.ycombinator.com/item?id=15363552</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 29 Sep 2017 08:05:51 +0000</pubDate><link>http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&amp;Sect2=HITOFF&amp;p=1&amp;u=%2Fnetahtml%2FPTO%2Fsearch-bool.html&amp;r=1&amp;f=G&amp;l=50&amp;co1=AND&amp;d=PTXT&amp;s1=%22System+method+addressing+overfitting+neural+network%22&amp;OS=</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=15363552</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=15363552</guid></item><item><title><![CDATA[New comment by tmulc18 in "How Booking.com manipulates users"]]></title><description><![CDATA[
<p>That's why you gotta use Expedia or Google</p>
]]></description><pubDate>Wed, 20 Sep 2017 22:43:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=15299028</link><dc:creator>tmulc18</dc:creator><comments>https://news.ycombinator.com/item?id=15299028</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=15299028</guid></item></channel></rss>