<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: pboulos</title><link>https://news.ycombinator.com/user?id=pboulos</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 09 Sep 2026 12:27:12 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=pboulos" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by pboulos in "DaVinci Resolve 21.1"]]></title><description><![CDATA[
<p>As an anecdote, I recently needed to colour-grade some short footage for personal purposes. My workflow at the time was to essentially ask an LLM for guidance on how to use DaVinci Resolve to perform the task, step by step. I would make an adjustment, take a screenshot of the controls and the result, and repeat that process a handful of times, eventually ending up with a pretty nice result.<p>I can definitely see the utility of something like this for cases where a media budget just wouldn't have existed in the first place.</p>
]]></description><pubDate>Tue, 08 Sep 2026 14:53:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=49611216</link><dc:creator>pboulos</dc:creator><comments>https://news.ycombinator.com/item?id=49611216</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49611216</guid></item><item><title><![CDATA[New comment by pboulos in "OpenAI says it has overtaken Anthropic with its latest AI model"]]></title><description><![CDATA[
<p>I actually created this post with a sharing link; it looks like it may have gotten blocked on FTs side.</p>
]]></description><pubDate>Thu, 03 Sep 2026 18:40:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=49554639</link><dc:creator>pboulos</dc:creator><comments>https://news.ycombinator.com/item?id=49554639</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49554639</guid></item><item><title><![CDATA[New comment by pboulos in "OpenAI says it has overtaken Anthropic with its latest AI model"]]></title><description><![CDATA[
<p>It seems as though this article was released prematurely. See the below excerpt:<p>"OpenAI on Thursday released its latest AI model, which it called “the world’s most intelligent”, as the ChatGPT maker aims to retake the lead from arch-rival Anthropic ahead of a planned public listing.<p>The $852bn start-up said GPT-6 Astra was market-leading in software engineering, science and cyber security — an increasingly critical field following multiple high-profile breaches in recent weeks.<p>The bullish launch for Astra marks OpenAI’s effort to signal that it believes it has regained the technical lead from Anthropic, which was founded five years ago by a group of senior OpenAI staff."</p>
]]></description><pubDate>Thu, 03 Sep 2026 18:40:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=49554624</link><dc:creator>pboulos</dc:creator><comments>https://news.ycombinator.com/item?id=49554624</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49554624</guid></item><item><title><![CDATA[OpenAI says it has overtaken Anthropic with its latest AI model]]></title><description><![CDATA[
<p>Article URL: <a href="https://giftarticle.ft.com/giftarticle/actions/redeem/1054f4f0-cac7-479c-a4a7-f95b3906ca4b">https://giftarticle.ft.com/giftarticle/actions/redeem/1054f4f0-cac7-479c-a4a7-f95b3906ca4b</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49554060">https://news.ycombinator.com/item?id=49554060</a></p>
<p>Points: 16</p>
<p># Comments: 7</p>
]]></description><pubDate>Thu, 03 Sep 2026 18:02:40 +0000</pubDate><link>https://giftarticle.ft.com/giftarticle/actions/redeem/1054f4f0-cac7-479c-a4a7-f95b3906ca4b</link><dc:creator>pboulos</dc:creator><comments>https://news.ycombinator.com/item?id=49554060</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49554060</guid></item><item><title><![CDATA[Anthropic and Amazon expand collaboration for up to 5 gigawatts of new compute]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.anthropic.com/news/anthropic-amazon-compute">https://www.anthropic.com/news/anthropic-amazon-compute</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47841684">https://news.ycombinator.com/item?id=47841684</a></p>
<p>Points: 6</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 20 Apr 2026 22:10:54 +0000</pubDate><link>https://www.anthropic.com/news/anthropic-amazon-compute</link><dc:creator>pboulos</dc:creator><comments>https://news.ycombinator.com/item?id=47841684</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47841684</guid></item><item><title><![CDATA[New comment by pboulos in "We replaced RAG with a virtual filesystem for our AI documentation assistant"]]></title><description><![CDATA[
<p>I agree with your assessment.</p>
]]></description><pubDate>Fri, 03 Apr 2026 19:25:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=47630999</link><dc:creator>pboulos</dc:creator><comments>https://news.ycombinator.com/item?id=47630999</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47630999</guid></item><item><title><![CDATA[New comment by pboulos in "We replaced RAG with a virtual filesystem for our AI documentation assistant"]]></title><description><![CDATA[
<p>I think this is a great approach for a startup like Mintlify. I do have skepticism around how practical this would be in some of the “messier” organisations where RAG stands to add the most value. From personal experience, getting RAG to work well in places where the structure of the organisation and the information contained therein is far from hierarchical or partition-able is a very hard task.</p>
]]></description><pubDate>Fri, 03 Apr 2026 18:04:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=47629921</link><dc:creator>pboulos</dc:creator><comments>https://news.ycombinator.com/item?id=47629921</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47629921</guid></item><item><title><![CDATA[I joined an Easter procession for the fitness and stayed for the faith]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.ft.com/content/edb8780c-7500-4112-a6bf-a7fcab908676">https://www.ft.com/content/edb8780c-7500-4112-a6bf-a7fcab908676</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47566508">https://news.ycombinator.com/item?id=47566508</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 29 Mar 2026 19:44:29 +0000</pubDate><link>https://www.ft.com/content/edb8780c-7500-4112-a6bf-a7fcab908676</link><dc:creator>pboulos</dc:creator><comments>https://news.ycombinator.com/item?id=47566508</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47566508</guid></item><item><title><![CDATA[PEP 827 – Type Manipulation]]></title><description><![CDATA[
<p>Article URL: <a href="https://peps.python.org/pep-0827/">https://peps.python.org/pep-0827/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47236012">https://news.ycombinator.com/item?id=47236012</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 03 Mar 2026 17:47:26 +0000</pubDate><link>https://peps.python.org/pep-0827/</link><dc:creator>pboulos</dc:creator><comments>https://news.ycombinator.com/item?id=47236012</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47236012</guid></item><item><title><![CDATA[What Should I Get Paid When a Chatbot Eats My Books?]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.nytimes.com/2025/09/13/opinion/culture/a-chatbot-ate-my-books-jackpot.html">https://www.nytimes.com/2025/09/13/opinion/culture/a-chatbot-ate-my-books-jackpot.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45235639">https://news.ycombinator.com/item?id=45235639</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 13 Sep 2025 21:54:11 +0000</pubDate><link>https://www.nytimes.com/2025/09/13/opinion/culture/a-chatbot-ate-my-books-jackpot.html</link><dc:creator>pboulos</dc:creator><comments>https://news.ycombinator.com/item?id=45235639</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45235639</guid></item></channel></rss>