<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: maxmaio</title><link>https://news.ycombinator.com/user?id=maxmaio</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 09 Apr 2026 12:39:02 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=maxmaio" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by maxmaio in "Project Glasswing: Securing critical software for the AI era"]]></title><description><![CDATA[
<p>seems important and terrifying. This morning Opus 4.6 was blowing my mind in claude code... onward and upward</p>
]]></description><pubDate>Tue, 07 Apr 2026 20:40:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=47681082</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=47681082</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47681082</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Freestyle: Sandboxes for AI Coding Agents"]]></title><description><![CDATA[
<p>Congrats Ben and Jacob!</p>
]]></description><pubDate>Mon, 06 Apr 2026 18:25:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=47664844</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=47664844</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47664844</guid></item><item><title><![CDATA[New comment by maxmaio in "CSS's problems are Tailwind's problems"]]></title><description><![CDATA[
<p>I use tailwind on all of my projects now and like it. I've used a lot of the css fads of the last decade (css in js was the worst which ironically is what the author recommends) and tailwind is the most ergonomic for me -and apparently most web devs considering how popular it is.<p>"Did you really say bundler?"
If you dont use a bundler this is a fair point. But I'm confident you do use one so adding tailwind is ~3 lines of code.</p>
]]></description><pubDate>Tue, 22 Jul 2025 16:47:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=44649765</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=44649765</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44649765</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data"]]></title><description><![CDATA[
<p>We are currently focused on business customers :/ but that may change in the coming months!</p>
]]></description><pubDate>Thu, 07 Nov 2024 17:07:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=42078542</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42078542</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42078542</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data"]]></title><description><![CDATA[
<p>We have seen a lot of use cases in finance and are currently working with a few firms. Accuracy is generally their primary requirement. We've been focusing on not just accuracy but also the audit experience which includes confidence scoring. Your right about security and we are currently undergoing a soc 2 audit.<p>Generally firms are outsourcing the data entry and are already manually auditing with shortcuts like summing values.<p>Relating to formatted in the table they expected. We extract the data directly into their template format so it is always in the table they expect.</p>
]]></description><pubDate>Thu, 07 Nov 2024 17:04:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=42078517</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42078517</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42078517</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data"]]></title><description><![CDATA[
<p>This is something we are hyper focused on. shoot me an email at max@midhsip.dev - you can also try our financial analysis template in our playground for free: <a href="https://app.midship.ai/demo">https://app.midship.ai/demo</a>.</p>
]]></description><pubDate>Thu, 07 Nov 2024 17:00:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=42078464</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42078464</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42078464</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data"]]></title><description><![CDATA[
<p>yes we can! shoot me an email max@midship.dev</p>
]]></description><pubDate>Thu, 07 Nov 2024 16:57:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=42078433</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42078433</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42078433</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data"]]></title><description><![CDATA[
<p>Hi! In our playground we only included a few templates, but in our app you can create any template you'd like! So yes we can extract from academic papers! shoot me an email: max@midship.dev</p>
]]></description><pubDate>Thu, 07 Nov 2024 16:56:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=42078425</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42078425</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42078425</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data"]]></title><description><![CDATA[
<p>Send me an email here: max@midship.dev so we can learn more.  We're in the process of a SOC 2 audit and should be HIPAA by end of the month!</p>
]]></description><pubDate>Thu, 07 Nov 2024 03:01:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=42072914</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42072914</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42072914</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data"]]></title><description><![CDATA[
<p>This is an interesting use case! We've heard similar stories from people dealing with pensions. Today we are ready to solve out of the box the extract data from a factsheet into excel or CSV step. Shoot me an email at max@midship.dev!</p>
]]></description><pubDate>Wed, 06 Nov 2024 22:36:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=42070619</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42070619</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42070619</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data"]]></title><description><![CDATA[
<p>We're excited for foundational models to improve because we hope it will unlock a lot more use cases. Things like analysis after extraction, able to accurately extract extremely complex documents, etc!</p>
]]></description><pubDate>Wed, 06 Nov 2024 21:32:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=42069753</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42069753</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42069753</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data"]]></title><description><![CDATA[
<p>We saw initial traction with real estate firms extracting property data like rent rolls. But we've also seen traction in other verticals like accounting and intake forms.  The original idea was very ambitious and when talking to potential customers they all seemed to be happy with the existing players.</p>
]]></description><pubDate>Wed, 06 Nov 2024 20:48:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=42069121</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42069121</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42069121</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn PDFs and Images into usable data"]]></title><description><![CDATA[
<p>+1 to what mitch said. We believe there is a large market for non-technical users who can now automate extraction tasks but do not know how to interact with apis. Midship is another option for them that requires 0 programming!</p>
]]></description><pubDate>Wed, 06 Nov 2024 19:35:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=42067996</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42067996</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42067996</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data"]]></title><description><![CDATA[
<p>The reducto guys are great! Their benchmark is not exactly how we would index our product because we extract into a user specified template vs. extracting into markdown (wysiwyg). That being said their eval aligns with our internal findings of commercial OCR offerings.</p>
]]></description><pubDate>Wed, 06 Nov 2024 19:26:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=42067872</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42067872</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42067872</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn PDFs and Images into usable data"]]></title><description><![CDATA[
<p>We currently support pdf, docx, most image types (jpeg/jpg, png, heic), and excel.<p>saving the email as a pdf would work!</p>
]]></description><pubDate>Wed, 06 Nov 2024 19:01:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=42067481</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42067481</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42067481</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data"]]></title><description><![CDATA[
<p>Yes there is definitely a boom in document related startups. We see our niche as focusing on non technical users. We have focused on making it easy to build schemas, an audit and review experience, and integrating into downstream applications.</p>
]]></description><pubDate>Wed, 06 Nov 2024 18:58:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=42067424</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42067424</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42067424</guid></item><item><title><![CDATA[New comment by maxmaio in "Launch HN: Midship (YC S24) – Turn unstructured documents into usable data"]]></title><description><![CDATA[
<p>Yes today we support exports to csv or excel from our web app!</p>
]]></description><pubDate>Wed, 06 Nov 2024 18:33:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=42067010</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42067010</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42067010</guid></item><item><title><![CDATA[Launch HN: Midship (YC S24) – Turn PDFs, docs, and images into usable data]]></title><description><![CDATA[
<p>Hey HN, we are Max, Kieran, and Aahel from Midship (<a href="https://midship.ai">https://midship.ai</a>). Midship makes it easy to extract data from unstructured documents like pdfs and images.<p>Here’s a video showing it in action: <a href="https://www.loom.com/share/ae43b6abfcc24e5b82c87104339f2625?sid=2f2cf0fa-d671-4590-992a-da51712c69e1" rel="nofollow">https://www.loom.com/share/ae43b6abfcc24e5b82c87104339f2625?...</a>, and a demo playground (no signup required!) to test it out: <a href="https://app.midship.ai/demo">https://app.midship.ai/demo</a><p>We started 5 months ago initially trying to make an AI natural language workflow builder that would be a simpler alternative to Zapier or Make.com. However, most of our users seemed to be much more interested in the basic (and not very good) document extraction feature we had. Seeing how people were spending hours a day manually extracting data from pdfs inspired us to build what has become Midship!<p>The problem is that despite all our progress in software, huge amounts of business data still lives in PDFs and images. Sure, you can OCR them, but getting clean, structured data out is still painful. Most existing tools just give you a blob of markdown - leaving you to figure out which parts matter and how they relate.<p>We've found that combining OCR with language models lets us do something more useful: extract specific fields and tables that users actually care about. The LLMs help correct OCR mistakes and understand context (like knowing that "Inv#" and "Invoice Number" mean the same thing).<p>We have two main kinds of users today, non-technical users that extract data via our web app and developers who use our extraction api.  We were initially focused on the first one as they seemed like an underserved part of the market, but we’ve received a lot of interest from developers who face the same issues.<p>For pricing, we currently charge a monthly Saas fee per seat for the web app and a volume based pricing for the API.<p>We’re really excited to share what we’ve built so far and look forward to any feedback from the community!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=42066500">https://news.ycombinator.com/item?id=42066500</a></p>
<p>Points: 121</p>
<p># Comments: 61</p>
]]></description><pubDate>Wed, 06 Nov 2024 18:05:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=42066500</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=42066500</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42066500</guid></item><item><title><![CDATA[Ask HN: What framework are people using for SPAs these days?]]></title><description><![CDATA[
<p>Now that create-react-app seems dead, what are people using for SPA. Note I have used next.js in the past but find it the wrong tool for a SPA. I love react but would love to hear what people are using</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=40734265">https://news.ycombinator.com/item?id=40734265</a></p>
<p>Points: 3</p>
<p># Comments: 2</p>
]]></description><pubDate>Thu, 20 Jun 2024 02:16:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=40734265</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=40734265</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40734265</guid></item><item><title><![CDATA[New comment by maxmaio in "Ask HN: What are the top BaaS (Back end as a Service) platforms in 2023"]]></title><description><![CDATA[
<p>Supabase is amazing</p>
]]></description><pubDate>Tue, 11 Apr 2023 18:33:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=35529280</link><dc:creator>maxmaio</dc:creator><comments>https://news.ycombinator.com/item?id=35529280</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35529280</guid></item></channel></rss>