<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: uri_merhav</title><link>https://news.ycombinator.com/user?id=uri_merhav</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 17 Nov 2026 03:08:46 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=uri_merhav" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by uri_merhav in "Countersigned – Free Alternative to Docusign"]]></title><description><![CDATA[
<p>It's annoying to pay $11 a MONTH to freaking sign a PDF, and scale to $30 for anything more than 5 envelopes. So we made this free.<p>Our commercial angle is to use this free tool to promote DocuSign. There's a paid tier if you need 100 envelopes a month. Still way cheaper than Docusign.<p>In terms of "should I trust you with my data" - we're the same team as DocuPipe, which has been around for 3 years and handles healthcare and financial document. In fact, this launch is basically a tool to help promote DocuPipe, which is our core product.<p>Was this vibe coded?<p>frontend: of course
backend: hell no. Subject to the same high security review that we conduct for our robust document processing DocuPipe<p>Hope you find this useful, and feedback very welcome</p>
]]></description><pubDate>Mon, 12 Oct 2026 14:30:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=50056992</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=50056992</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50056992</guid></item><item><title><![CDATA[Countersigned – Free Alternative to Docusign]]></title><description><![CDATA[
<p>Article URL: <a href="https://countersigned.io">https://countersigned.io</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50056991">https://news.ycombinator.com/item?id=50056991</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 12 Oct 2026 14:30:45 +0000</pubDate><link>https://countersigned.io</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=50056991</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50056991</guid></item><item><title><![CDATA[Show HN: Free PDF Document Redaction]]></title><description><![CDATA[
<p>Hey, I made this tool. Pop in a PDF and redact what you need, edit results if needed, etc.<p>My angle here is that people use it for free and promote to use all other things DocuPipe can do for you.<p>Why not stick to GPT and be done with it? GPT/Claude doesn't work reliably even remotely, and you can't edit results.<p>Tool is SOC-2 and ISO certified for infosec, we don't train on your data, etc.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48823107">https://news.ycombinator.com/item?id=48823107</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 07 Jul 2026 20:16:38 +0000</pubDate><link>https://www.docupipe.ai/tools/redact-pdf</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=48823107</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48823107</guid></item><item><title><![CDATA[Show HN: Document to Excel Converter]]></title><description><![CDATA[
<p>I built a free tool to convert a PDF to excel. It's more nuanced than first meets the eye: a document can not contain any tables but still lend itself to becoming one or more excel sheets (e.g. a rental contract can be a list of renter names, or a doctor's note may contain a list of allergies and a list of diagnoses).<p>Anticipating the obvious question of "why can't I just shove this into GPT" - DocuPipe is far better accuracy (see benchmark [here](<a href="https://github.com/DocuPipe/DocuBench" rel="nofollow">https://github.com/DocuPipe/DocuBench</a>)), especially on longer documents. And it lets you orchestrate complex workflows, and get repeatable results.<p>One more thing - your data is your own, documents are not retained, we'd never train on it, and the entire solution is SOC-2 certified for security best practices.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48769060">https://news.ycombinator.com/item?id=48769060</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 03 Jul 2026 00:10:50 +0000</pubDate><link>https://www.docupipe.ai/tools/pdf-to-excel</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=48769060</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48769060</guid></item><item><title><![CDATA[New comment by uri_merhav in "Show HN: PageIndex – Vectorless RAG"]]></title><description><![CDATA[
<p>Try DocuPipe. It blows Gemini out of the water in terms of accuracy in extracting . They also generate a page + bounding box for every extracted field.</p>
]]></description><pubDate>Sun, 07 Sep 2025 01:10:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=45154383</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=45154383</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45154383</guid></item><item><title><![CDATA[New comment by uri_merhav in "Voidware: Software that only exists when you use it"]]></title><description><![CDATA[
<p>Very cool demo.<p>But isn't the point of an app being able to maintain a sharable worldview and state?<p>This "improvised just for you" sounds like a natural fit for a text adventure for example, but I'm still grappling with how this might apply to a real life use case.<p>One can conceivably imagine imagine LLMs one day transforming states for sharing on-the-fly as well, but it does sound very fragile.</p>
]]></description><pubDate>Mon, 14 Jul 2025 15:25:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=44561293</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=44561293</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44561293</guid></item><item><title><![CDATA[New comment by uri_merhav in "Why LLMs still have problems with OCR"]]></title><description><![CDATA[
<p>There's lots of hidden gotchas to this. Uploading a screenshot and asking an LLM to transcribe one page is generally ok. Give it a table that spans pages, or a 60 page doc, and you're in dire straits.<p>I cofounded DocuPanda to handle this issue specifically. Call me biased, but I do believe it's the best solution out there.</p>
]]></description><pubDate>Sat, 08 Feb 2025 15:00:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=42983347</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=42983347</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42983347</guid></item><item><title><![CDATA[New comment by uri_merhav in "Ingesting PDFs and why Gemini 2.0 changes everything"]]></title><description><![CDATA[
<p>Gemini Flash 2.0 is impressive but it hardly captures all of the information in the PDF. It's great for getting vibes from the document or finding overall information in it. If you ask it to e.g. enumerate every line item from multiple tables in a long PDF it still falls flat (dropping some line items or entire sections etc). DocuPanda and to a lesser extent Unstrucutred handle this.</p>
]]></description><pubDate>Fri, 07 Feb 2025 19:48:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=42976697</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=42976697</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42976697</guid></item><item><title><![CDATA[New comment by uri_merhav in "DocuPanda – convert any PDF/image to a schema-driven, structured JSONs"]]></title><description><![CDATA[
<p>Very strong table extraction, and a developer-focused approach where the AI helps you figure out a good schema to systematically extract the same fields from documents in all layouts.</p>
]]></description><pubDate>Fri, 09 Aug 2024 14:54:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=41202454</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=41202454</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41202454</guid></item><item><title><![CDATA[DocuPanda – convert any PDF/image to a schema-driven, structured JSONs]]></title><description><![CDATA[
<p>Article URL: <a href="https://docupanda.com/app/login/">https://docupanda.com/app/login/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=41202453">https://news.ycombinator.com/item?id=41202453</a></p>
<p>Points: 16</p>
<p># Comments: 4</p>
]]></description><pubDate>Fri, 09 Aug 2024 14:54:27 +0000</pubDate><link>https://docupanda.com/app/login/</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=41202453</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41202453</guid></item><item><title><![CDATA[New comment by uri_merhav in "I built an AI Sales Engineer"]]></title><description><![CDATA[
<p>Awesome stuff, looks very cool. I liked their focus on reducing hallucinations, that stuff is often overlooked by people rushing into building AI proof of concepts.</p>
]]></description><pubDate>Wed, 24 Apr 2024 19:12:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=40148317</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=40148317</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40148317</guid></item><item><title><![CDATA[New comment by uri_merhav in "Automated video background removal and transcription"]]></title><description><![CDATA[
<p>Gets the job done. I think it's better than unscreen.com</p>
]]></description><pubDate>Wed, 29 Mar 2023 04:49:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=35352755</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=35352755</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35352755</guid></item><item><title><![CDATA[Automated video background removal and transcription]]></title><description><![CDATA[
<p>Article URL: <a href="https://photobear.io/video_background_removal">https://photobear.io/video_background_removal</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=35352754">https://news.ycombinator.com/item?id=35352754</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Wed, 29 Mar 2023 04:49:41 +0000</pubDate><link>https://photobear.io/video_background_removal</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=35352754</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35352754</guid></item><item><title><![CDATA[New comment by uri_merhav in "Choose your own adventure using GPT with automatically generated illustrations"]]></title><description><![CDATA[
<p>Please try again. Slight outage due to sudden shift in traffic volume</p>
]]></description><pubDate>Thu, 08 Dec 2022 04:06:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=33904016</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=33904016</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33904016</guid></item><item><title><![CDATA[Choose your own adventure using GPT with automatically generated illustrations]]></title><description><![CDATA[
<p>Article URL: <a href="https://mytales.io/">https://mytales.io/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=33903817">https://news.ycombinator.com/item?id=33903817</a></p>
<p>Points: 2</p>
<p># Comments: 2</p>
]]></description><pubDate>Thu, 08 Dec 2022 03:32:27 +0000</pubDate><link>https://mytales.io/</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=33903817</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33903817</guid></item><item><title><![CDATA[New comment by uri_merhav in "Dalle-2 type technology puts photos on custom backgrounds"]]></title><description><![CDATA[
<p>I'm the site's founder and happy to take hear any and all feedback.<p>The underlying technology is called diffusion models. I'm sure many on HN have already hear of it - it's the technology underlying all these neat text to image results in DALLE-2, Imagen, and the open source counterpart called Stable Diffusion.<p>Getting this technology to embed real life images in arbitrary backgrounds has been quite the challenge, but it's already showing some pretty neat results which you can check out on the website. Currently we support Christmas setup, and white background with shadows and reflections. We'll add a plenty more background categories in the immediate future.</p>
]]></description><pubDate>Tue, 01 Nov 2022 06:01:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=33417528</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=33417528</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33417528</guid></item><item><title><![CDATA[New comment by uri_merhav in "Dalle-2 type technology puts photos on custom backgrounds"]]></title><description><![CDATA[
<p>I'm the site's founder - happy to hear you're impressed with the background removal. I think it's pretty much on par with remove.bg, which are the most famous competitor in the category.<p>Couldn't help but notice you omitted any reference to the major technological achievement here in placing objects on arbitrary backgrounds. It failed to impress on your use case?</p>
]]></description><pubDate>Tue, 01 Nov 2022 05:57:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=33417506</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=33417506</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33417506</guid></item><item><title><![CDATA[Dalle-2 type technology puts photos on custom backgrounds]]></title><description><![CDATA[
<p>Article URL: <a href="https://photobear.io/">https://photobear.io/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=33417343">https://news.ycombinator.com/item?id=33417343</a></p>
<p>Points: 3</p>
<p># Comments: 4</p>
]]></description><pubDate>Tue, 01 Nov 2022 05:33:56 +0000</pubDate><link>https://photobear.io/</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=33417343</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33417343</guid></item><item><title><![CDATA[New comment by uri_merhav in "AI based background removal API - remove.bg competitor"]]></title><description><![CDATA[
<p>Kind of like remove.bg but with a friendlier pricepoint. It also does photo vectorization and super resolution.</p>
]]></description><pubDate>Thu, 10 Feb 2022 16:41:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=30288769</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=30288769</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=30288769</guid></item><item><title><![CDATA[AI based background removal API - remove.bg competitor]]></title><description><![CDATA[
<p>Article URL: <a href="https://photobear.io/background_removal">https://photobear.io/background_removal</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=30288768">https://news.ycombinator.com/item?id=30288768</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 10 Feb 2022 16:41:37 +0000</pubDate><link>https://photobear.io/background_removal</link><dc:creator>uri_merhav</dc:creator><comments>https://news.ycombinator.com/item?id=30288768</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=30288768</guid></item></channel></rss>