<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: f_k</title><link>https://news.ycombinator.com/user?id=f_k</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 15 Apr 2026 11:11:04 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=f_k" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by f_k in "Ask HN: What Are You Working On? (April 2026)"]]></title><description><![CDATA[
<p><a href="https://citellm.com" rel="nofollow">https://citellm.com</a><p>Building CiteLLM, an API that extracts structured data from PDFs and returns exact source locations for every field.<p>There's also a widget so you can add click-to-verify to your own app in a few lines of code.<p>Click any value, jump straight to the highlighted source in the PDF.<p>Demo: <a href="https://citellm.com/demo" rel="nofollow">https://citellm.com/demo</a></p>
]]></description><pubDate>Mon, 13 Apr 2026 21:33:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=47758098</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=47758098</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47758098</guid></item><item><title><![CDATA[New comment by f_k in "Ask HN: What Are You Working On? (March 2026)"]]></title><description><![CDATA[
<p><a href="https://citellm.com" rel="nofollow">https://citellm.com</a><p>Building CiteLLM, an API that extracts structured data from PDFs and returns exact source locations for every field.<p>There's also a widget so you can add click-to-verify to your own app in a few lines of code.<p>Click any value, jump straight to the highlighted source in the PDF.<p>Demo: <a href="https://citellm.com/demo" rel="nofollow">https://citellm.com/demo</a></p>
]]></description><pubDate>Mon, 09 Mar 2026 11:00:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=47307432</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=47307432</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47307432</guid></item><item><title><![CDATA[New comment by f_k in "Ask HN: What are you working on? (February 2026)"]]></title><description><![CDATA[
<p><a href="https://citellm.com" rel="nofollow">https://citellm.com</a><p>Building CiteLLM, an API that extracts structured data from PDFs and returns exact source locations for every field.<p>It comes with an embeddable widget so you can add click-to-verify to your own app in a few lines of code.<p>Click any value, jump straight to the highlighted source in the PDF.<p>Demo: <a href="https://citellm.com/demo" rel="nofollow">https://citellm.com/demo</a></p>
]]></description><pubDate>Mon, 09 Feb 2026 00:31:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=46940114</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=46940114</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46940114</guid></item><item><title><![CDATA[New comment by f_k in "Ask HN: What are you working on? (January 2026)"]]></title><description><![CDATA[
<p><a href="https://citellm.com" rel="nofollow">https://citellm.com</a><p>Working on CiteLLM, an API that extracts structured data from PDFs and returns citations for each field (page + coordinates + source snippet + confidence).<p>Instead of blindly trusting the LLM, you can verify every value by linking it back to its exact location in the original PDF.</p>
]]></description><pubDate>Sun, 11 Jan 2026 20:37:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=46579749</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=46579749</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46579749</guid></item><item><title><![CDATA[New comment by f_k in "Ask HN: Is anyone using LLM based document processing in production?"]]></title><description><![CDATA[
<p>I'm working on this exact problem with <a href="https://citellm.com" rel="nofollow">https://citellm.com</a> .<p>Every extracted field comes with a precise citation back to the source document (page + snippet + bounding box + confidence score) so reviewers can verify where each value came from.<p>Hallucinations get flagged automatically because there's no supporting text in the source.<p>The goal is to make HITL fast and not have reviewers read through the whole document.</p>
]]></description><pubDate>Fri, 19 Dec 2025 04:07:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=46322167</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=46322167</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46322167</guid></item><item><title><![CDATA[New comment by f_k in "Ask HN: What Are You Working On? (December 2025)"]]></title><description><![CDATA[
<p><a href="https://citellm.com" rel="nofollow">https://citellm.com</a><p>Working on CiteLLM, an API that extracts structured data from PDFs and returns citations for each field (page + coordinates + source snippet + confidence).<p>Instead of blindly trusting the LLM, you can verify every value by linking it back to its exact location in the original PDF.</p>
]]></description><pubDate>Mon, 15 Dec 2025 20:02:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=46279729</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=46279729</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46279729</guid></item><item><title><![CDATA[New comment by f_k in "GPT-5.2"]]></title><description><![CDATA[
<p>> verifying their claims ends up taking time.<p>I've been working on this problem with <a href="https://citellm.com" rel="nofollow">https://citellm.com</a>, specifically for PDFs.<p>Instead of relying on the LLM answer alone, each extracted field links to its source in the original document (page number + highlighted snippet + confidence score).<p>Checking any claim becomes simple: click and see the exact source.</p>
]]></description><pubDate>Sat, 13 Dec 2025 02:10:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=46251335</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=46251335</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46251335</guid></item><item><title><![CDATA[Show HN: SuperCurate – Fast note search and curation]]></title><description><![CDATA[
<p>I'm building SuperCurate (<a href="https://getsupercurate.com" rel="nofollow">https://getsupercurate.com</a>), a tool focused on note retrieval and curation rather than note creation. Think filing cabinet for your notes, web clippings, images and PDFs.<p>I built it because I wanted fast search and filters for my Evernote archive (ENEX) so I could drill down and surface exactly what I was looking for.<p>It can also search inside PDFs and jump directly to the matching page with highlights.<p>Web Clipper for Chrome to save content directly:
<a href="https://chromewebstore.google.com/detail/piianedlaigjpcebhlpgcpccjmfbafib" rel="nofollow">https://chromewebstore.google.com/detail/piianedlaigjpcebhlp...</a><p>Demos:<p>- Search and curation: <a href="https://www.youtube.com/watch?v=z4QSIoUL4Uk" rel="nofollow">https://www.youtube.com/watch?v=z4QSIoUL4Uk</a><p>- Web Clipper: <a href="https://www.youtube.com/watch?v=8F7QoC7X3fs" rel="nofollow">https://www.youtube.com/watch?v=8F7QoC7X3fs</a><p>- Search inside PDFs: <a href="https://www.youtube.com/watch?v=t0X9sD-938Q" rel="nofollow">https://www.youtube.com/watch?v=t0X9sD-938Q</a><p>I'd love to hear your feedback and use cases!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45876407">https://news.ycombinator.com/item?id=45876407</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 10 Nov 2025 14:34:48 +0000</pubDate><link>https://getsupercurate.com</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=45876407</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45876407</guid></item><item><title><![CDATA[New comment by f_k in "Ask HN: What Are You Working On? (Nov 2025)"]]></title><description><![CDATA[
<p>I'm working on SuperCurate (<a href="https://getsupercurate.com" rel="nofollow">https://getsupercurate.com</a>), which is geared towards note retrieval and curation rather than note creation.
Think filing cabinet for your notes, web clippings, images and PDFs.<p>I wanted fast search and filters for my Evernote archive so I could drill down and surface exactly what I was looking for.<p>There's also a Web Clipper extension for Chrome.<p>Demos:<p>Search and curation: <a href="https://www.youtube.com/watch?v=z4QSIoUL4Uk" rel="nofollow">https://www.youtube.com/watch?v=z4QSIoUL4Uk</a><p>Web Clipper: <a href="https://www.youtube.com/watch?v=8F7QoC7X3fs" rel="nofollow">https://www.youtube.com/watch?v=8F7QoC7X3fs</a><p>Search inside PDFs (jumps to page + highlights snippet): <a href="https://www.youtube.com/watch?v=t0X9sD-938Q" rel="nofollow">https://www.youtube.com/watch?v=t0X9sD-938Q</a><p>It's free while in beta, would love feedback if you try it.</p>
]]></description><pubDate>Mon, 10 Nov 2025 00:01:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=45870590</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=45870590</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45870590</guid></item><item><title><![CDATA[Show HN: Chrome extension to save YouTube timestamps with transcripts]]></title><description><![CDATA[
<p>Article URL: <a href="https://chromewebstore.google.com/detail/youtube-segment-clipper/mkmcjgbighammmaoohbieijiolllnefn">https://chromewebstore.google.com/detail/youtube-segment-clipper/mkmcjgbighammmaoohbieijiolllnefn</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44663522">https://news.ycombinator.com/item?id=44663522</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 23 Jul 2025 20:17:30 +0000</pubDate><link>https://chromewebstore.google.com/detail/youtube-segment-clipper/mkmcjgbighammmaoohbieijiolllnefn</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=44663522</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44663522</guid></item><item><title><![CDATA[Show HN: Chrome extension to save YouTube segments with captions]]></title><description><![CDATA[
<p>Article URL: <a href="https://chromewebstore.google.com/detail/youtube-segment-clipper/mkmcjgbighammmaoohbieijiolllnefn">https://chromewebstore.google.com/detail/youtube-segment-clipper/mkmcjgbighammmaoohbieijiolllnefn</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44637131">https://news.ycombinator.com/item?id=44637131</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 21 Jul 2025 16:31:11 +0000</pubDate><link>https://chromewebstore.google.com/detail/youtube-segment-clipper/mkmcjgbighammmaoohbieijiolllnefn</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=44637131</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44637131</guid></item><item><title><![CDATA[New comment by f_k in "Mistral OCR"]]></title><description><![CDATA[
<p><a href="https://getsearchablepdf.com" rel="nofollow">https://getsearchablepdf.com</a> (I'm the founder)</p>
]]></description><pubDate>Sat, 08 Mar 2025 13:15:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=43299996</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=43299996</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43299996</guid></item><item><title><![CDATA[New comment by f_k in "Mistral OCR"]]></title><description><![CDATA[
<p>Shameless plug: <a href="https://getsearchablepdf.com" rel="nofollow">https://getsearchablepdf.com</a></p>
]]></description><pubDate>Sat, 08 Mar 2025 13:13:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=43299988</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=43299988</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43299988</guid></item><item><title><![CDATA[New comment by f_k in "Show HN: LLM-aided OCR – Correcting Tesseract OCR errors with LLMs"]]></title><description><![CDATA[
<p>We've built an app like that but for PDF table extraction, <a href="https://table2xl.com" rel="nofollow">https://table2xl.com</a></p>
]]></description><pubDate>Fri, 09 Aug 2024 17:14:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=41203683</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=41203683</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41203683</guid></item><item><title><![CDATA[New comment by f_k in "Ask HN: How to transcribe 1000s of handwritten notes"]]></title><description><![CDATA[
<p>Shameless plug: <a href="https://getsearchablepdf.com" rel="nofollow">https://getsearchablepdf.com</a><p>There's a free trial so you can check if it works for your handwriting.</p>
]]></description><pubDate>Sat, 01 Jun 2024 17:44:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=40547677</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=40547677</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40547677</guid></item><item><title><![CDATA[New comment by f_k in "Running OCR against PDFs and images directly in the browser"]]></title><description><![CDATA[
<p>If you're on Windows try <a href="https://table2xl.com" rel="nofollow">https://table2xl.com</a> (disclosure: I'm the founder), it's more accurate than Excel's camera import. No API though.</p>
]]></description><pubDate>Sun, 31 Mar 2024 12:50:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=39883798</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=39883798</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39883798</guid></item><item><title><![CDATA[Show HN: Bulk PDF OCR made easy]]></title><description><![CDATA[
<p>How it works:<p>1. Connect Dropbox/OneDrive account (or use the web uploader).<p>2. Drag n drop PDF files to the Input folder.<p>3. Get searchable PDFs in Output folder.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=39241715">https://news.ycombinator.com/item?id=39241715</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 03 Feb 2024 16:16:10 +0000</pubDate><link>https://getsearchablepdf.com</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=39241715</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39241715</guid></item><item><title><![CDATA[Show HN: Bulk PDF OCR made easy]]></title><description><![CDATA[
<p>How it works:<p>1. Connect Dropbox/OneDrive account (or use the web uploader).<p>2. Drag n drop PDF files to the Input folder.<p>3. Get searchable PDFs in Output folder.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=39121508">https://news.ycombinator.com/item?id=39121508</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 24 Jan 2024 19:20:20 +0000</pubDate><link>https://getsearchablepdf.com</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=39121508</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39121508</guid></item><item><title><![CDATA[Show HN: Easiest way to convert PDF tables to Excel]]></title><description><![CDATA[
<p>We built a Windows app to convert PDF tables to Excel. You just have to take a screenshot of the table.<p>Why try another app when there's so many PDF to Excel converters? 
It is:
- Faster
- More convenient
- More accurate than other converters (including Excel's Power Query).<p>Feel free to test it with complex tables (like the ones found in financial documents).</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=37070319">https://news.ycombinator.com/item?id=37070319</a></p>
<p>Points: 6</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 10 Aug 2023 00:35:49 +0000</pubDate><link>https://table2xl.com</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=37070319</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37070319</guid></item><item><title><![CDATA[New comment by f_k in "Show HN: Fastest way to convert a PDF table to Excel"]]></title><description><![CDATA[
<p>Feel free to try it with complex tables (like the ones found in financial documents).</p>
]]></description><pubDate>Sat, 22 Jul 2023 21:06:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=36829952</link><dc:creator>f_k</dc:creator><comments>https://news.ycombinator.com/item?id=36829952</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=36829952</guid></item></channel></rss>