<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: jaan</title><link>https://news.ycombinator.com/user?id=jaan</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 15 May 2026 08:45:05 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=jaan" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by jaan in "Googlebook"]]></title><description><![CDATA[
<p>Wow, I’m in the same boat - do you mind sharing more about how you did it? I was thinking about that too (I’m 197cm) and would love to learn!</p>
]]></description><pubDate>Tue, 12 May 2026 21:52:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=48115103</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=48115103</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48115103</guid></item><item><title><![CDATA[New comment by jaan in "Music for Programming"]]></title><description><![CDATA[
<p>NTS radio has been incredible for programming music over the years. Deep backlog, an ambient channel (infinite mixtape: <a href="https://www.nts.live/infinite-mixtapes/slow-focus" rel="nofollow">https://www.nts.live/infinite-mixtapes/slow-focus</a>), and great selections:<p><a href="https://www.nts.live/" rel="nofollow">https://www.nts.live/</a><p>And they have mobile apps :)</p>
]]></description><pubDate>Mon, 06 Apr 2026 17:46:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=47664324</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=47664324</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47664324</guid></item><item><title><![CDATA[New comment by jaan in "Show HN: Prompts as WASM Programs"]]></title><description><![CDATA[
<p>Does it support constrained generation during training?<p>This is what we need for the large language models I am training for health care use cases.<p>For example, constraining LLM output is currently done by masking, and having this rust based library would enable novel ways to train LLMs.<p>Relevant papers:<p><a href="https://github.com/epfl-dlab/transformers-CFG">https://github.com/epfl-dlab/transformers-CFG</a><p><a href="https://neurips.cc/virtual/2023/poster/70782" rel="nofollow">https://neurips.cc/virtual/2023/poster/70782</a></p>
]]></description><pubDate>Mon, 11 Mar 2024 22:44:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=39674067</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=39674067</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39674067</guid></item><item><title><![CDATA[Show HN: Teaching myself baby plain text accounting with large language models]]></title><description><![CDATA[
<p>I finally took this community's advice after reading about plain text accounting for years but being too scared to dive in. I timeboxed it to an hour or two this weekend and thankfully large language models are more than up to the task! If anyone has done similar things or already solved this problem I'm all ears. Next up will be a dashboard using Observable Framework with this transactions data (<a href="https://observablehq.com/framework/;" rel="nofollow">https://observablehq.com/framework/;</a> made a demo here: <a href="https://jaanli.github.io/american-community-survey/income" rel="nofollow">https://jaanli.github.io/american-community-survey/income</a>). Open to any feedback/tips if you have done this before or are less fearful of accounting!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=39662693">https://news.ycombinator.com/item?id=39662693</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 10 Mar 2024 21:33:16 +0000</pubDate><link>https://gist.github.com/jaanli/1f735ce0ddec4aa4d1fccb4535f3843f</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=39662693</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39662693</guid></item><item><title><![CDATA[New comment by jaan in "Observable 2.0, a static site generator for data apps"]]></title><description><![CDATA[
<p>Also trying to figure this out for using it with vite! Added a question here: <a href="https://github.com/observablehq/framework/discussions/855">https://github.com/observablehq/framework/discussions/855</a></p>
]]></description><pubDate>Sun, 18 Feb 2024 12:53:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=39418633</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=39418633</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39418633</guid></item><item><title><![CDATA[New comment by jaan in "Visualization of 106,000 prices at NYC hospital shows cost differences"]]></title><description><![CDATA[
<p>Open to any feedback on this here or over email (jaan@onefact.org)!<p>I quit academia to start a non-profit focused on using open source to analyze the public hospital price transparency data.<p>We are now making similar dashboards for every hospital in the country, and need all the help we can get if you would be interested in using the latest geospatial mapping tools, databases (duckdb) and large language models to make sense of this massive amount of data.<p>Through a data bounty (<a href="https://www.dolthub.com/repositories/onefact/paylesshealth" rel="nofollow noreferrer">https://www.dolthub.com/repositories/onefact/paylesshealth</a>) we collected 4000+ hospital price sheets and made them public here: <a href="https://data.payless.health/#hospital_price_transparency/" rel="nofollow noreferrer">https://data.payless.health/#hospital_price_transparency/</a>. This was on HN previously.<p>Grateful for all your support so far!!</p>
]]></description><pubDate>Mon, 14 Aug 2023 18:00:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=37124304</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=37124304</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37124304</guid></item><item><title><![CDATA[Visualization of 106,000 prices at NYC hospital shows cost differences]]></title><description><![CDATA[
<p>Article URL: <a href="https://beta.payless.health/examples/mount-sinai.html">https://beta.payless.health/examples/mount-sinai.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=37124303">https://news.ycombinator.com/item?id=37124303</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 14 Aug 2023 18:00:29 +0000</pubDate><link>https://beta.payless.health/examples/mount-sinai.html</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=37124303</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37124303</guid></item><item><title><![CDATA[New comment by jaan in "Couldn't afford custom domain URL shorteners – open-sourced our S3 free approach"]]></title><description><![CDATA[
<p>Bitly was expensive, so this is a fun little use case for redirect rules for subdomains. Was coming increasingly handy as we scale our nonprofit, so wanted to share and open sourced this!</p>
]]></description><pubDate>Wed, 10 May 2023 03:25:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=35883285</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=35883285</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35883285</guid></item><item><title><![CDATA[Couldn't afford custom domain URL shorteners – open-sourced our S3 free approach]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/onefact/free-url-shortening-on-amazon-s3-on-free-tier">https://github.com/onefact/free-url-shortening-on-amazon-s3-on-free-tier</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=35883284">https://news.ycombinator.com/item?id=35883284</a></p>
<p>Points: 4</p>
<p># Comments: 1</p>
]]></description><pubDate>Wed, 10 May 2023 03:25:33 +0000</pubDate><link>https://github.com/onefact/free-url-shortening-on-amazon-s3-on-free-tier</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=35883284</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35883284</guid></item><item><title><![CDATA[New comment by jaan in "Open-source hospital price transparency"]]></title><description><![CDATA[
<p>Wow. Would love to help you build this and pay you for Apache 2.0 release of your work with our grant money - emailing you now :)</p>
]]></description><pubDate>Wed, 07 Dec 2022 09:22:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=33892338</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=33892338</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33892338</guid></item><item><title><![CDATA[New comment by jaan in "Open-source hospital price transparency"]]></title><description><![CDATA[
<p>Yes! We are working on this and integrating with the OMOP common data model, to be able to link the health outcomes in our data partners' clinical repositories to the cost of care. For example, we work with the NIH All of Us study for outcome data (joinallofus.org -- I signed up both to contribute to this science and to get my whole genome sequenced free!)</p>
]]></description><pubDate>Tue, 06 Dec 2022 21:45:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=33887512</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=33887512</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33887512</guid></item><item><title><![CDATA[New comment by jaan in "Open-source hospital price transparency"]]></title><description><![CDATA[
<p>You're right! We're linking this data to the negiotated rates :) and building the search engine for both of these at payless.health.</p>
]]></description><pubDate>Tue, 06 Dec 2022 21:43:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=33887494</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=33887494</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33887494</guid></item><item><title><![CDATA[New comment by jaan in "Open-source hospital price transparency"]]></title><description><![CDATA[
<p>Nailed it! :)</p>
]]></description><pubDate>Tue, 06 Dec 2022 21:31:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=33887353</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=33887353</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33887353</guid></item><item><title><![CDATA[New comment by jaan in "Open-source hospital price transparency"]]></title><description><![CDATA[
<p>If you look at the files, many of them are not compliant, and so we need to figure out what the associated line item corresponds to: a CPT code? HCPCS code? ICD code? etc :)<p>Here's an example NLP tool I helped build we're using to do this: <a href="https://arxiv.org/abs/1904.05342" rel="nofollow">https://arxiv.org/abs/1904.05342</a> -- it's in several pipelines now for data annotation and crowdsourcing.</p>
]]></description><pubDate>Tue, 06 Dec 2022 21:31:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=33887346</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=33887346</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33887346</guid></item><item><title><![CDATA[New comment by jaan in "Ask HN: What is your “I don't care if this succeeds” project?"]]></title><description><![CDATA[
<p>I got a friend to record guided meditations geared at techbros: <a href="https://dystopia.guide/" rel="nofollow">https://dystopia.guide/</a><p>Really meant as a critique of late stage capitalism where companies like Headspace have ads in New York encouraging us to “optimize” our mindfulness practice so we can train harder…</p>
]]></description><pubDate>Fri, 11 Feb 2022 03:46:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=30296663</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=30296663</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=30296663</guid></item><item><title><![CDATA[My friend radicalized. This made me rethink how I build AI]]></title><description><![CDATA[
<p>Article URL: <a href="https://jaan.io/my-friend-radicalized-this-made-me-rethink-how-i-build-AI/">https://jaan.io/my-friend-radicalized-this-made-me-rethink-how-i-build-AI/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=25942226">https://news.ycombinator.com/item?id=25942226</a></p>
<p>Points: 23</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 28 Jan 2021 14:30:31 +0000</pubDate><link>https://jaan.io/my-friend-radicalized-this-made-me-rethink-how-i-build-AI/</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=25942226</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=25942226</guid></item><item><title><![CDATA[How to rid your life of algorithmic bias and not become data for AI]]></title><description><![CDATA[
<p>Article URL: <a href="https://jaan.io/dont-become-data-for-AI/">https://jaan.io/dont-become-data-for-AI/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=25908148">https://news.ycombinator.com/item?id=25908148</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 25 Jan 2021 20:14:05 +0000</pubDate><link>https://jaan.io/dont-become-data-for-AI/</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=25908148</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=25908148</guid></item><item><title><![CDATA[New comment by jaan in "Food2vec – Augmented cooking with machine intelligence"]]></title><description><![CDATA[
<p>Thank you! Just fixed it, hosting it on S3 now.</p>
]]></description><pubDate>Tue, 24 Jan 2017 19:56:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=13474879</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=13474879</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=13474879</guid></item><item><title><![CDATA[Food2vec – Augmented cooking with machine intelligence]]></title><description><![CDATA[
<p>Article URL: <a href="https://jaan.io/food2vec-augmented-cooking-machine-intelligence/">https://jaan.io/food2vec-augmented-cooking-machine-intelligence/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=13472721">https://news.ycombinator.com/item?id=13472721</a></p>
<p>Points: 29</p>
<p># Comments: 3</p>
]]></description><pubDate>Tue, 24 Jan 2017 16:27:40 +0000</pubDate><link>https://jaan.io/food2vec-augmented-cooking-machine-intelligence/</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=13472721</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=13472721</guid></item><item><title><![CDATA[The Confusion of Variational Autoencoders]]></title><description><![CDATA[
<p>Article URL: <a href="https://jaan.io/unreasonable-confusion/">https://jaan.io/unreasonable-confusion/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=12292576">https://news.ycombinator.com/item?id=12292576</a></p>
<p>Points: 52</p>
<p># Comments: 11</p>
]]></description><pubDate>Mon, 15 Aug 2016 18:53:49 +0000</pubDate><link>https://jaan.io/unreasonable-confusion/</link><dc:creator>jaan</dc:creator><comments>https://news.ycombinator.com/item?id=12292576</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=12292576</guid></item></channel></rss>