<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: rabisg</title><link>https://news.ycombinator.com/user?id=rabisg</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 18 Nov 2026 19:30:49 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=rabisg" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by rabisg in "OpenUI: Open Standard for Generative UI"]]></title><description><![CDATA[
<p>The language is platform independent and the parsers and renderers are open source with the intention of letting people fork out into their own language. Would love your support in extending it to other platforms</p>
]]></description><pubDate>Fri, 10 Jul 2026 14:00:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=48860058</link><dc:creator>rabisg</dc:creator><comments>https://news.ycombinator.com/item?id=48860058</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48860058</guid></item><item><title><![CDATA[New comment by rabisg in "OpenUI: Open Standard for Generative UI"]]></title><description><![CDATA[
<p>Hey @bel8
Founder of Thesys here - company behind OpenUI. its designed to be very customizable but if you hit a roadblock please open an issue on GH and we'd be happy to patch it</p>
]]></description><pubDate>Fri, 10 Jul 2026 13:59:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=48860031</link><dc:creator>rabisg</dc:creator><comments>https://news.ycombinator.com/item?id=48860031</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48860031</guid></item><item><title><![CDATA[New comment by rabisg in "We rewrote our Rust WASM parser in TypeScript and it got faster"]]></title><description><![CDATA[
<p>My experience is from trying to get the React Native example to work with OpenUI. Felt Sonnet/Opus was much better at figuring out whats wrong with the current React implementation and fixing it than it was with React Native<p>But yes I see what you mean and I think people are trying to solve it with skills and harnesses at the application layer but its not there yet</p>
]]></description><pubDate>Sat, 21 Mar 2026 15:16:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=47467803</link><dc:creator>rabisg</dc:creator><comments>https://news.ycombinator.com/item?id=47467803</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47467803</guid></item><item><title><![CDATA[New comment by rabisg in "We rewrote our Rust WASM parser in TypeScript and it got faster"]]></title><description><![CDATA[
<p>We tried all formats - XML, json, jsonl, even toon - before deciding that we need to invest in OpenUI Lang<p>The primary motivation was speed and schema cohesion. We were running a JSON based format, Thesys C1, in production for a year before we realized we cannot add features fast enough because we were fighting the LLMs at multiple levels. It's probably too much to write in a comment but we'd like to write about the motivation and all the things we tried ona a separate blog soon</p>
]]></description><pubDate>Sat, 21 Mar 2026 13:37:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=47466919</link><dc:creator>rabisg</dc:creator><comments>https://news.ycombinator.com/item?id=47466919</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47466919</guid></item><item><title><![CDATA[New comment by rabisg in "We rewrote our Rust WASM parser in TypeScript and it got faster"]]></title><description><![CDATA[
<p>Haven't looked in depth but yes it feels like they are solving the same problem.<p>This is an alternative to json-render by Vercel or A2UI by Google which I'm guessing the flutter implementation is based on</p>
]]></description><pubDate>Sat, 21 Mar 2026 13:33:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=47466884</link><dc:creator>rabisg</dc:creator><comments>https://news.ycombinator.com/item?id=47466884</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47466884</guid></item><item><title><![CDATA[New comment by rabisg in "We rewrote our Rust WASM parser in TypeScript and it got faster"]]></title><description><![CDATA[
<p>as an author of the blog - ouch
did a little bit more than prompt claude but a lot of claude prompting was definitely involved<p>I understand your frustration with AI writing though. We are a small team and given our roadmap it was either use LLMs to help collate all the internal benchmark results file into a blog or never write it so we chose the former. This was a genuinely surprising and counterintuitive result for us, which is why we wanted to share it. Happy to clarify any of the numbers if helpful.</p>
]]></description><pubDate>Sat, 21 Mar 2026 07:25:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=47464787</link><dc:creator>rabisg</dc:creator><comments>https://news.ycombinator.com/item?id=47464787</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47464787</guid></item><item><title><![CDATA[New comment by rabisg in "We rewrote our Rust WASM parser in TypeScript and it got faster"]]></title><description><![CDATA[
<p>(author here) We'd be really surprised if a rewrite could fix the boundary tax but if it does, we'd happily move over to it. People (including me) really underestimate how insanely fast browser's JSON.parse is</p>
]]></description><pubDate>Sat, 21 Mar 2026 07:13:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=47464720</link><dc:creator>rabisg</dc:creator><comments>https://news.ycombinator.com/item?id=47464720</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47464720</guid></item><item><title><![CDATA[New comment by rabisg in "We rewrote our Rust WASM parser in TypeScript and it got faster"]]></title><description><![CDATA[
<p>Its the library that bridges the gap between LLMs and live UI. Best example would be to imagine you want to build interactive charts within your AI agent (like Claude)<p>The most obvious approach would be to let LLMs generate code and render it but that introduces problems like safety, UI consistency and speed. OpenUI solves those problems and provides a safe, consistent and token optimized runtime for the LLMs to render live UI</p>
]]></description><pubDate>Sat, 21 Mar 2026 07:07:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=47464686</link><dc:creator>rabisg</dc:creator><comments>https://news.ycombinator.com/item?id=47464686</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47464686</guid></item><item><title><![CDATA[New comment by rabisg in "We rewrote our Rust WASM parser in TypeScript and it got faster"]]></title><description><![CDATA[
<p>One of the authors here. While that’s generally true, in this case it wasn’t time that helped us learn what worked. It was a nagging sense that the architecture wasn’t right, just days before launch, along with heavy instrumentation to test our assumptions.</p>
]]></description><pubDate>Sat, 21 Mar 2026 07:01:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=47464652</link><dc:creator>rabisg</dc:creator><comments>https://news.ycombinator.com/item?id=47464652</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47464652</guid></item><item><title><![CDATA[New comment by rabisg in "We rewrote our Rust WASM parser in TypeScript and it got faster"]]></title><description><![CDATA[
<p>The last part is really interesting. It feels like the whole world will soon become Python/JS because thats what LLMs are good at. Very few people will then take the pain of optimizing it</p>
]]></description><pubDate>Sat, 21 Mar 2026 06:51:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=47464599</link><dc:creator>rabisg</dc:creator><comments>https://news.ycombinator.com/item?id=47464599</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47464599</guid></item><item><title><![CDATA[Show HN: C1 – an OpenAI-compatible LLM API that renders real UI instead of md]]></title><description><![CDATA[
<p>We’ve been working on C1, an OpenAI-compatible API that returns real UI components—buttons, forms, layouts—instead of markdown or plain text. The goal is to help developers build agents and copilots that go beyond conversation and support real interaction, without writing front-end glue code.<p>It works like a regular chat completion endpoint: pass in a prompt and tools, get back a structured UI that users can click, fill out, or navigate.<p>Explainer video: https://www.youtube.com/watch?v=jHqTyXwm58c
Link to docs: https://docs.thesys.dev/guides/solutions/chat<p>Would love feedback from anyone building LLM-powered interfaces or agentic tools.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43965164">https://news.ycombinator.com/item?id=43965164</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 12 May 2025 17:02:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=43965164</link><dc:creator>rabisg</dc:creator><comments>https://news.ycombinator.com/item?id=43965164</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43965164</guid></item></channel></rss>