<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: hidude562</title><link>https://news.ycombinator.com/user?id=hidude562</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 08 Oct 2026 02:06:40 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=hidude562" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by hidude562 in "An OMR model 6x more accurate at 1/30 the size"]]></title><description><![CDATA[
<p>Thank you! I have respect for soundslice for also furthering the field. Cheers</p>
]]></description><pubDate>Tue, 06 Oct 2026 19:53:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=49983211</link><dc:creator>hidude562</dc:creator><comments>https://news.ycombinator.com/item?id=49983211</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49983211</guid></item><item><title><![CDATA[New comment by hidude562 in "An OMR model 6x more accurate at 1/30 the size"]]></title><description><![CDATA[
<p>I made a OMR (optical music recognition) model that outperforms the next leading released model (legato) on quartet scans by 6x.  It's 28m parameters, with a 2m parameter harness, vs legato which is 100m parameters but with a 900m vision encoder strapped on.</p>
]]></description><pubDate>Tue, 06 Oct 2026 18:25:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=49982193</link><dc:creator>hidude562</dc:creator><comments>https://news.ycombinator.com/item?id=49982193</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49982193</guid></item><item><title><![CDATA[An OMR model 6x more accurate at 1/30 the size]]></title><description><![CDATA[
<p>Article URL: <a href="https://kobi.music/research/copista">https://kobi.music/research/copista</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49982192">https://news.ycombinator.com/item?id=49982192</a></p>
<p>Points: 1</p>
<p># Comments: 3</p>
]]></description><pubDate>Tue, 06 Oct 2026 18:25:36 +0000</pubDate><link>https://kobi.music/research/copista</link><dc:creator>hidude562</dc:creator><comments>https://news.ycombinator.com/item?id=49982192</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49982192</guid></item><item><title><![CDATA[New comment by hidude562 in "Find the flattest route between any two points in SF"]]></title><description><![CDATA[
<p>you could mathematically find the least bikeable city using this lol</p>
]]></description><pubDate>Tue, 06 Oct 2026 04:22:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=49974148</link><dc:creator>hidude562</dc:creator><comments>https://news.ycombinator.com/item?id=49974148</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49974148</guid></item><item><title><![CDATA[New comment by hidude562 in "Learning Jazz Pianist Style with Cross-Attention Conditioning"]]></title><description><![CDATA[
<p>this is cool don't listen to the haters. wonder if you can embed the chords / context somehow so it can play with real music?</p>
]]></description><pubDate>Tue, 06 Oct 2026 04:11:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=49974070</link><dc:creator>hidude562</dc:creator><comments>https://news.ycombinator.com/item?id=49974070</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49974070</guid></item></channel></rss>