<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: superdocs1</title><link>https://news.ycombinator.com/user?id=superdocs1</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 26 Jun 2026 01:57:24 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=superdocs1" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by superdocs1 in "Ask HN: Who wants to be hired? (June 2026)"]]></title><description><![CDATA[
<p>Location: Europe<p>Remote: Yes (flexible with time zone differences & async work)<p>Willing to relocate: No<p>Technologies: Python, TypeScript, Next.js, C#, LLMs, Document Processing, OCR, Image Processing, NLP, AWS, Azure, Docker<p>Résumé/CV: <a href="https://superdocs.io" rel="nofollow">https://superdocs.io</a><p>Email: superdocsio@gmail.com<p>I specialize in document processing, I can help with:<p><pre><code>  - Data extraction from documents
  - OCR
  - LLMs, RAG, Structured Extraction
  - Table detection/recognition
  - Document classification
  - Document splitting
</code></pre>
Currently working on <a href="https://citellm.com" rel="nofollow">https://citellm.com</a>, an API that adds citations to LLM structured extraction, so users can click-to-verify any value.<p>Available for freelance work.</p>
]]></description><pubDate>Thu, 04 Jun 2026 21:32:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=48404913</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=48404913</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48404913</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: Who wants to be hired? (May 2026)"]]></title><description><![CDATA[
<p>Location: Europe<p>Remote: Yes (flexible with time zone differences & async work)<p>Willing to relocate: No<p>Technologies: Python, TypeScript, Next.js, C#, LLMs, Document Processing, OCR, Image Processing, NLP, AWS, Azure, Docker<p>Résumé/CV: <a href="https://superdocs.io" rel="nofollow">https://superdocs.io</a><p>Email: superdocsio@gmail.com<p>I specialize in "AI for documents", available for freelance work on:<p><pre><code>  - LLMs, RAG, Structured Extraction
  - Data extraction from documents
  - OCR
  - Table detection/recognition
  - Document classification
  - Document splitting
  - PDF workflow automation
</code></pre>
Currently working on <a href="https://citellm.com" rel="nofollow">https://citellm.com</a>, an API that adds citations to LLM structured extraction, so users can click-to-verify any value.</p>
]]></description><pubDate>Thu, 07 May 2026 21:33:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=48055392</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=48055392</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48055392</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: Who wants to be hired? (April 2026)"]]></title><description><![CDATA[
<p>Location: Europe<p>Remote: Yes (flexible with time zone differences & async work)<p>Willing to relocate: No<p>Technologies: Python, TypeScript, Next.js, C#, LLMs, Document Processing, OCR, Image Processing, NLP, AWS, Azure, Docker<p>Résumé/CV: <a href="https://superdocs.io" rel="nofollow">https://superdocs.io</a><p>Email: superdocsio@gmail.com<p>I specialize in "AI for documents", available for freelance work on:<p><pre><code>  - LLMs, RAG, Structured Extraction
  - Data extraction from documents
  - OCR
  - Table detection/recognition
  - Document classification
  - Document splitting
  - PDF workflow automation
</code></pre>
Currently working on <a href="https://citellm.com" rel="nofollow">https://citellm.com</a>, an API that adds citations to LLM structured extraction, so users can click-to-verify any value.</p>
]]></description><pubDate>Wed, 01 Apr 2026 23:01:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=47607687</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=47607687</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47607687</guid></item><item><title><![CDATA[New comment by superdocs1 in "OCR for construction documents does not work, we fixed it"]]></title><description><![CDATA[
<p>Interesting, I've dealt with a similar problem before. If anyone needs a self-hosted/custom solution, feel free to reach out.</p>
]]></description><pubDate>Wed, 01 Apr 2026 22:53:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=47607585</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=47607585</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47607585</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: Who wants to be hired? (March 2026)"]]></title><description><![CDATA[
<p>Location: Europe<p>Remote: Yes (flexible with time zone differences & async work)<p>Willing to relocate: No<p>Technologies: Python, TypeScript, Next.js, C#, LLMs, Document Processing, OCR, Image Processing, NLP, AWS, Azure, Docker<p>Résumé/CV: <a href="https://superdocs.io" rel="nofollow">https://superdocs.io</a><p>Email: superdocsio@gmail.com<p>I specialize in "AI for documents", available for consulting on:<p><pre><code>  - LLMs, RAG, Structured Extraction
  - Data extraction from documents
  - OCR
  - Table detection/recognition
  - Document classification
  - Document splitting
  - PDF workflow automation
</code></pre>
Currently working on <a href="https://citellm.com" rel="nofollow">https://citellm.com</a>, an API that adds citations to LLM document extraction, so users can click-to-verify any value.</p>
]]></description><pubDate>Mon, 02 Mar 2026 23:08:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=47225567</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=47225567</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47225567</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: Who wants to be hired? (February 2026)"]]></title><description><![CDATA[
<p>Location: Europe<p>Remote: Yes (flexible with time zone differences & async work)<p>Willing to relocate: No<p>Technologies: Python, TypeScript, Next.js, C#, LLMs, Document Processing, OCR, Image Processing, NLP, AWS, Azure, Docker<p>Résumé/CV: <a href="https://superdocs.io" rel="nofollow">https://superdocs.io</a><p>Email: superdocsio@gmail.com<p>I specialize in "AI for documents", available for consulting on:<p><pre><code>  - LLMs, RAG, Structured Extraction
  - Data extraction from documents
  - OCR
  - Table detection/recognition
  - Document classification
  - Document splitting
  - PDF workflow automation
</code></pre>
Currently working on <a href="https://citellm.com" rel="nofollow">https://citellm.com</a>, an API that adds citations to LLM document extraction, so users can click-to-verify any value.</p>
]]></description><pubDate>Mon, 02 Feb 2026 19:33:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=46860186</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=46860186</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46860186</guid></item><item><title><![CDATA[New comment by superdocs1 in "I hate screenshots of text"]]></title><description><![CDATA[
<p><a href="https://screenshotocr.app" rel="nofollow">https://screenshotocr.app</a> does this on Windows (I'm the founder).</p>
]]></description><pubDate>Thu, 20 Nov 2025 00:19:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=45987157</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=45987157</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45987157</guid></item><item><title><![CDATA[Show HN: SuperCurate – Fast note search and curation]]></title><description><![CDATA[
<p>I'm building SuperCurate, a tool focused on note retrieval and curation. Think filing cabinet for your notes, web clippings, images and PDFs.<p>Key features:<p>- Import from Evernote (ENEX), MD, PDF, images<p>- Fast search with filters to quickly find what you're looking for<p>- Organize notes into collections<p>- Search inside PDFs with direct page jumping and highlighting<p>- SuperCurate Web Clipper (similar to Evernote Web Clipper) extension for Chrome to save content directly to your library<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=45931854">https://news.ycombinator.com/item?id=45931854</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 14 Nov 2025 20:33:51 +0000</pubDate><link>https://getsupercurate.com</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=45931854</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45931854</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: Freelancer? Seeking freelancer? (October 2025)"]]></title><description><![CDATA[
<p>SEEKING WORK | Europe | Remote<p>I'm a freelance consultant specializing in document processing.<p>I can help with:<p><pre><code>  - LLMs, RAG, Structured Extraction
  - Data extraction from PDF documents
  - OCR projects
  - Table detection/recognition
  - Document classification
  - Document splitting
  - PDF workflow automation
</code></pre>
Email: superdocsio@gmail.com<p>Web: <a href="https://superdocs.io" rel="nofollow">https://superdocs.io</a></p>
]]></description><pubDate>Thu, 02 Oct 2025 09:28:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=45447715</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=45447715</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45447715</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: What are you working on? (September 2025)"]]></title><description><![CDATA[
<p>Built an app that lets you search inside Youtube videos and jump to the specific moments where something was mentioned.<p>For example "Paul Graham interview best founders" will surface moments where pg talks about founder qualities: <a href="https://www.youtube.com/watch?v=BXqk9QaV-ag" rel="nofollow">https://www.youtube.com/watch?v=BXqk9QaV-ag</a></p>
]]></description><pubDate>Tue, 30 Sep 2025 16:52:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=45427931</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=45427931</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45427931</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: Freelancer? Seeking freelancer? (September 2025)"]]></title><description><![CDATA[
<p>SEEKING WORK | Europe | Remote<p>I'm a freelance consultant specializing in document processing.<p>I can help with:<p><pre><code>  - LLMs, RAG, Structured Extraction
  - Data extraction from PDF documents
  - OCR projects
  - Table detection/recognition
  - Document classification
  - Document splitting
  - PDF workflow automation
</code></pre>
Email: superdocsio@gmail.com<p>Web: <a href="https://superdocs.io" rel="nofollow">https://superdocs.io</a></p>
]]></description><pubDate>Tue, 02 Sep 2025 20:30:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=45108589</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=45108589</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45108589</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: Freelancer? Seeking freelancer? (August 2025)"]]></title><description><![CDATA[
<p>SEEKING WORK | Europe | Remote<p>I'm a freelance consultant specializing in document processing.<p>Currently building an app that extracts key information from PDFs and automatically highlights the source text for each extracted data point, allowing users to easily verify the accuracy of the extracted information.<p>I can help with:<p><pre><code>  - LLMs, RAG, Structured Extraction
  - Data extraction from PDF documents
  - OCR projects
  - Table detection/recognition
  - Document classification
  - Document splitting
  - PDF workflow automation
</code></pre>
Email: superdocsio@gmail.com<p>Web: <a href="https://superdocs.io" rel="nofollow">https://superdocs.io</a></p>
]]></description><pubDate>Fri, 01 Aug 2025 20:40:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=44762236</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=44762236</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44762236</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: What are you working on? (July 2025)"]]></title><description><![CDATA[
<p>Also built an app that lets you search inside Youtube videos and jump to the specific moments where something was mentioned.<p>For example:
"Paul Graham interview best founders" (surfaces moments where pg talks about founder qualities): <a href="https://www.youtube.com/watch?v=BXqk9QaV-ag" rel="nofollow">https://www.youtube.com/watch?v=BXqk9QaV-ag</a></p>
]]></description><pubDate>Mon, 28 Jul 2025 04:32:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=44707251</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=44707251</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44707251</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: What are you working on? (July 2025)"]]></title><description><![CDATA[
<p>I built Youtube Segment Clipper, a free Chrome extension to save parts of YouTube videos with timestamps and transcripts.<p><a href="https://chromewebstore.google.com/detail/mkmcjgbighammmaoohbieijiolllnefn" rel="nofollow">https://chromewebstore.google.com/detail/mkmcjgbighammmaoohb...</a></p>
]]></description><pubDate>Sun, 27 Jul 2025 22:25:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=44705284</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=44705284</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44705284</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: Freelancer? Seeking freelancer? (July 2025)"]]></title><description><![CDATA[
<p>SEEKING WORK | Europe | Remote<p>I'm a freelance consultant specializing in document processing.<p>Currently building an app that extracts key information from PDFs and automatically highlights the source text for each extracted data point, allowing users to easily verify the accuracy of the extracted information.<p>I can help with:<p><pre><code>  - LLMs, RAG, Structured Extraction
  - Data extraction from PDF documents
  - OCR projects
  - Table detection/recognition
  - Document classification
  - Document splitting
  - PDF workflow automation
</code></pre>
Email: superdocsio@gmail.com<p>Web: <a href="https://superdocs.io" rel="nofollow">https://superdocs.io</a></p>
]]></description><pubDate>Tue, 01 Jul 2025 21:40:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=44438245</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=44438245</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44438245</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: What Are You Working On? (June 2025)"]]></title><description><![CDATA[
<p>Building an app that extracts key information from PDFs + highlights citations.
You provide a PDF and a JSON schema defining what to extract, and it returns the extracted values, the citations and their precise locations in the document.<p>This is especially valuable in workflows where verification of LLM extracted information is critical (e.g. legal and finance). It can handle complex layouts like multiple columns, tables and also scanned documents.<p>Planning to offer this both as an API and a self-hosted option for organizations with strict data privacy requirements.<p>Screenshot: <a href="https://superdocs.io/highlight.png" rel="nofollow">https://superdocs.io/highlight.png</a></p>
]]></description><pubDate>Mon, 30 Jun 2025 15:15:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=44424365</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=44424365</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44424365</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: Freelancer? Seeking freelancer? (June 2025)"]]></title><description><![CDATA[
<p>SEEKING WORK | Europe | Remote<p>I'm a freelance consultant specializing in document processing.<p>Currently building an app that extracts key information from PDFs and automatically highlights the source text for each extracted data point, allowing users to easily verify the accuracy of the extracted information.<p>I can help with:<p><pre><code>  - LLMs, RAG, Structured Extraction
  - Data extraction from PDF documents
  - OCR projects
  - Table detection/recognition
  - Document classification
  - Document splitting
  - PDF workflow automation
</code></pre>
Email: superdocsio@gmail.com<p>Web: <a href="https://superdocs.io" rel="nofollow">https://superdocs.io</a></p>
]]></description><pubDate>Tue, 03 Jun 2025 03:24:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=44165971</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=44165971</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44165971</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: Freelancer? Seeking freelancer? (May 2025)"]]></title><description><![CDATA[
<p>SEEKING WORK | Europe | Remote<p>I'm a freelance consultant specializing in document processing.<p>Currently building an app that extracts key information from PDFs and automatically highlights the source text for each extracted data point, allowing users to easily verify the accuracy of the extracted information.<p>I can help with:<p><pre><code>  - LLMs, RAG, Structured Extraction
  - Data extraction from PDF documents
  - OCR projects
  - Table detection/recognition
  - Document classification
  - Document splitting
  - PDF workflow automation
</code></pre>
Email: superdocsio@gmail.com<p>Web: <a href="https://superdocs.io" rel="nofollow">https://superdocs.io</a></p>
]]></description><pubDate>Thu, 01 May 2025 17:12:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=43860511</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=43860511</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43860511</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: What are you working on? (April 2025)"]]></title><description><![CDATA[
<p>Building an app that extracts key information from PDFs + highlights citations.<p>You provide a PDF and a JSON schema defining what to extract, and it returns the extracted values, the citations and their precise locations in the document.<p>This is especially valuable in workflows where verification of LLM extracted information is critical (e.g. legal and finance). 
It can handle complex layouts like multiple columns, tables and also scanned documents.<p>Planning to offer this both as an API and a self-hosted option for organizations with strict data privacy requirements.<p>Screenshot: <a href="https://superdocs.io/highlight.png" rel="nofollow">https://superdocs.io/highlight.png</a><p>Feel free to get in touch for a demo.</p>
]]></description><pubDate>Mon, 28 Apr 2025 16:39:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=43823338</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=43823338</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43823338</guid></item><item><title><![CDATA[New comment by superdocs1 in "Ask HN: Freelancer? Seeking freelancer? (April 2025)"]]></title><description><![CDATA[
<p>SEEKING WORK | Europe | Remote<p>I'm a freelance consultant specializing in document processing.<p>Currently building an app that extracts key information from PDFs and automatically highlights the source text for each extracted data point, allowing users to easily verify the accuracy of the extracted information.<p>I can help with:<p><pre><code>  - LLMs, RAG, Structured Extraction
  - Data extraction from PDF documents
  - OCR projects
  - Table detection/recognition
  - Document classification
  - Document splitting
  - PDF workflow automation
</code></pre>
Email: superdocsio@gmail.com<p>Web: <a href="https://superdocs.io" rel="nofollow">https://superdocs.io</a></p>
]]></description><pubDate>Tue, 01 Apr 2025 16:57:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=43549032</link><dc:creator>superdocs1</dc:creator><comments>https://news.ycombinator.com/item?id=43549032</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43549032</guid></item></channel></rss>