<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: ac1spkrbox</title><link>https://news.ycombinator.com/user?id=ac1spkrbox</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 07 Apr 2026 05:59:55 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=ac1spkrbox" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by ac1spkrbox in "Do not download the app, use the website"]]></title><description><![CDATA[
<p>The website is often user-hostile, in hopes of pushing you to the app.</p>
]]></description><pubDate>Sat, 26 Jul 2025 03:01:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=44690957</link><dc:creator>ac1spkrbox</dc:creator><comments>https://news.ycombinator.com/item?id=44690957</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44690957</guid></item><item><title><![CDATA[New comment by ac1spkrbox in "LLaVA-O1: Let Vision Language Models Reason Step-by-Step"]]></title><description><![CDATA[
<p>Multimodal models are useful for lots of things! They can accomplish a range a tasks from zero-shot image classification to helping perform Retrieval-Augmented Generation on images. Like many generative model, I find the utility comes not necessarily from outperforming a human, but from scaling a task that a human wouldn't want to do (or won't do cheaply).</p>
]]></description><pubDate>Tue, 19 Nov 2024 14:31:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=42183818</link><dc:creator>ac1spkrbox</dc:creator><comments>https://news.ycombinator.com/item?id=42183818</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42183818</guid></item><item><title><![CDATA[General OCR Theory: Towards OCR-2.0 via a Unified End-to-End Model]]></title><description><![CDATA[
<p>Article URL: <a href="https://huggingface.co/papers/2409.01704">https://huggingface.co/papers/2409.01704</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=41514428">https://news.ycombinator.com/item?id=41514428</a></p>
<p>Points: 31</p>
<p># Comments: 2</p>
]]></description><pubDate>Wed, 11 Sep 2024 19:12:09 +0000</pubDate><link>https://huggingface.co/papers/2409.01704</link><dc:creator>ac1spkrbox</dc:creator><comments>https://news.ycombinator.com/item?id=41514428</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41514428</guid></item><item><title><![CDATA[New comment by ac1spkrbox in "Solving the out-of-context chunk problem for RAG"]]></title><description><![CDATA[
<p>The set of techniques for retrieval is immature, but it's important to note that just relying on model context or few-shot prompting has many drawbacks. Perhaps the most important is that retrieval as a task should not rely on generative outputs.</p>
]]></description><pubDate>Wed, 24 Jul 2024 12:52:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=41056556</link><dc:creator>ac1spkrbox</dc:creator><comments>https://news.ycombinator.com/item?id=41056556</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41056556</guid></item><item><title><![CDATA[New comment by ac1spkrbox in "Gemini AI"]]></title><description><![CDATA[
<p>“Any man who must say ‘I am the king’ is no true King”</p>
]]></description><pubDate>Wed, 06 Dec 2023 19:43:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=38548533</link><dc:creator>ac1spkrbox</dc:creator><comments>https://news.ycombinator.com/item?id=38548533</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38548533</guid></item><item><title><![CDATA[Solara: Pure Python, React-Style Framework for Scaling Your Jupyter and Web Apps]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/widgetti/solara">https://github.com/widgetti/solara</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=36917648">https://news.ycombinator.com/item?id=36917648</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 29 Jul 2023 07:00:43 +0000</pubDate><link>https://github.com/widgetti/solara</link><dc:creator>ac1spkrbox</dc:creator><comments>https://news.ycombinator.com/item?id=36917648</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=36917648</guid></item><item><title><![CDATA[New comment by ac1spkrbox in "How to Hire Good Engineers"]]></title><description><![CDATA[
<p>I’m much more interested in my actual work than personal projects. Is that so weird?<p>And it should go without saying that sharing employer code could be considered theft.</p>
]]></description><pubDate>Tue, 26 Jul 2022 01:26:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=32233203</link><dc:creator>ac1spkrbox</dc:creator><comments>https://news.ycombinator.com/item?id=32233203</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=32233203</guid></item><item><title><![CDATA[New comment by ac1spkrbox in "Google Buys Fitbit for $2.1B"]]></title><description><![CDATA[
<p>I'm confused by this comment.<p>To me, Garmin is the only company here that does a good job with the "hardcore fitness" market, but why does that matter in the first place? The better market to compete in is the "fitness amateur" market, which I see as being many times the former in size. Fitbit competes well here, and Google has no offering to speak of. Seems like a successful diversification move for Alphabet's portfolio. I especially like what Google's software can do to improve FitBit's offering by leveraging AI.</p>
]]></description><pubDate>Fri, 01 Nov 2019 14:00:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=21418860</link><dc:creator>ac1spkrbox</dc:creator><comments>https://news.ycombinator.com/item?id=21418860</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=21418860</guid></item></channel></rss>