<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: jxaphx</title><link>https://news.ycombinator.com/user?id=jxaphx</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 04 Jul 2026 16:48:24 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=jxaphx" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by jxaphx in "Show HN: Kate's App"]]></title><description><![CDATA[
<p>IANAL and this advice is only applicable to US/HIPAA rules based on my experience building and consulting in this space.<p>HIPAA rules apply to covered entities, and the developer of this app does not appear to be a covered entity. If a covered entity used this service, THEY would be required to enter into a Business Associate Agreement (BAA) with the developer, at which point the developer is on the hook and HIPAA applies.<p>If a covered entity engages with a platform like this, without a BAA, the liability under HIPAA is borne by the Covered Entity whom the rules apply to.<p>That said - if you want to engage with covered entities (and I think that should be a goal) you'll need to have all your ducks in a row before they'll be interested. It's all doable though, dont let the gatekeepers push you out.<p>One thing I've got my eye on right now is Palantir's HealthStart initiative that seeks to streamline the compliance requirements needed to operate in this space legally. Might be worth following if you plan to take this anywhere beyond a hobby.<p>Last note - my statement here is only about HIPAA. There are any number of state and federal level privacy rules where liability may or may not come into play here. Have a privacy policy, follow it, protect other people's data.If you're not confident you know how to do that, find someone who is. We do have a responsibility to our users that goes well beyond our desire to learn and experiment.<p>Good luck!</p>
]]></description><pubDate>Sun, 12 Jan 2025 01:39:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=42670471</link><dc:creator>jxaphx</dc:creator><comments>https://news.ycombinator.com/item?id=42670471</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42670471</guid></item><item><title><![CDATA[New comment by jxaphx in "GPT-4 Turbo with Vision Generally Available"]]></title><description><![CDATA[
<p>This has made a huge difference in the way we extract structured data from images. Previously we had to perform a number of steps to ensure the JSON result was what we were looking for. Now we just get the function call exactly where we expect it.<p>If you're a C# developer looking to take advantage of this improvement, check out our free open-source implementation at <a href="https://github.com/BackslashDev-LLC/img-to-json">https://github.com/BackslashDev-LLC/img-to-json</a> and our sample application at <a href="https://github.com/BackslashDev-LLC/med-intake-demo">https://github.com/BackslashDev-LLC/med-intake-demo</a></p>
]]></description><pubDate>Wed, 17 Apr 2024 08:15:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=40061832</link><dc:creator>jxaphx</dc:creator><comments>https://news.ycombinator.com/item?id=40061832</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40061832</guid></item><item><title><![CDATA[New comment by jxaphx in "Ask HN: Grow a profit-generating SaaS or work on a promising new one?"]]></title><description><![CDATA[
<p>As someone in a similar boat, my advice would be to start working on just driving attention/traffic to each one and see what the market tells you. It doesn't matter than your more recent idea is not as far along, there are lot of opportunities for lead generation outside of actually using the product (scorecards, waiting lists, etc...)<p>It doesn't matter how great either idea is if you can't get people to look at it. Focus there.</p>
]]></description><pubDate>Thu, 22 Feb 2024 20:52:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=39473057</link><dc:creator>jxaphx</dc:creator><comments>https://news.ycombinator.com/item?id=39473057</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39473057</guid></item><item><title><![CDATA[Show HN: Open-Source C# Library to Extract Structured Data from OpenAI API]]></title><description><![CDATA[
<p>Historically, we've done a lot of OCR work with mixed results in the .NET ecosystem. There were always a lot of tradeoffs. We were super excited when the GPT4V was announced, and quickly saw a lot of potential for data extraction from images.  There are a few pitfalls though. Primarily, GPT4V does not currently support tooling (i.e. function calling) and you cannot specify that you expect a JSON result in the API call.<p>...set aside the fact that good OpenAI libraries for .NET are hard to come by...<p>After looking over the way function calling works in completions, we realized we could do the same basic thing against GPT4V. Essentially, we annotate a simple class with a few attribtutes to instruct the API in what we want to accomplish. Then, we convert the object into a JSON schema specification and pass that in the prompt.<p>This has worked pretty well for us, and we've used it in a number of client projects. While I am sure that OpenAI will eventually support all of this directly through the API, I hope that some of our .NET brethren find it useful in the meantime!<p>The library is distributed via nuget, and the GitHub repo includes the library code as well as a simple demo app to check out the functionality locally.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=39360058">https://news.ycombinator.com/item?id=39360058</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 13 Feb 2024 17:18:39 +0000</pubDate><link>https://github.com/BackslashDev-LLC/img-to-json</link><dc:creator>jxaphx</dc:creator><comments>https://news.ycombinator.com/item?id=39360058</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39360058</guid></item></channel></rss>