<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: pbw</title><link>https://news.ycombinator.com/user?id=pbw</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 06 Apr 2026 02:17:18 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=pbw" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by pbw in "The threat is comfortable drift toward not understanding what you're doing"]]></title><description><![CDATA[
<p>There's certainly a risk that an individual will rely too much on AI, to the detriment of their ability to understand things. However, I think there are obvious counter-measures. For example, requiring that the student can explain every single intermediate step and every single figure in detail.<p>A two-hour thesis defense isn't enough to uncover this, but a 40-hour deep probing examination by an AI might be. And the thesis committee gets a "highlight reel" of all the places the student fell short.<p>The general pattern is: "Suppose we change nothing but add extensive use of AI, look how everything falls apart." When in reality, science and education are complex adaptive systems that will change as much as needed to absorb the impact of AI.</p>
]]></description><pubDate>Sun, 05 Apr 2026 14:00:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=47649560</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=47649560</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47649560</guid></item><item><title><![CDATA[New comment by pbw in "The future of version control"]]></title><description><![CDATA[
<p>This sounds good, but I wonder if AI has changed the calculus on conflict resolution. It can not only chase down the conflicting changes, but also read those commit messages and PRs to divine intent. It might be that git is "good enough," given we have AI.</p>
]]></description><pubDate>Sun, 22 Mar 2026 23:07:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=47483287</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=47483287</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47483287</guid></item><item><title><![CDATA[Technological Speed Limit]]></title><description><![CDATA[
<p>Article URL: <a href="https://metastable.org/speed-limit/">https://metastable.org/speed-limit/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47461601">https://news.ycombinator.com/item?id=47461601</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 20 Mar 2026 22:31:47 +0000</pubDate><link>https://metastable.org/speed-limit/</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=47461601</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47461601</guid></item><item><title><![CDATA[Coding with agents feels like a chess simul]]></title><description><![CDATA[
<p>Article URL: <a href="https://tobeva.com/articles/chess-simul/">https://tobeva.com/articles/chess-simul/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47413902">https://news.ycombinator.com/item?id=47413902</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 17 Mar 2026 15:17:58 +0000</pubDate><link>https://tobeva.com/articles/chess-simul/</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=47413902</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47413902</guid></item><item><title><![CDATA[The Technological Speed Limit]]></title><description><![CDATA[
<p>Article URL: <a href="https://metastable.org/speed-limit/">https://metastable.org/speed-limit/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47324889">https://news.ycombinator.com/item?id=47324889</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 10 Mar 2026 15:49:25 +0000</pubDate><link>https://metastable.org/speed-limit/</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=47324889</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47324889</guid></item><item><title><![CDATA[Show HN: Movie site built on a game engine]]></title><description><![CDATA[
<p>I'm an ex-gamedev (Guitar Hero) who built a movie website that looks like a Trello board. Each column can contain a different movie or cast member. Load pre-made boards or create your own by dragging and dropping between the columns. You can share boards with others.<p>For example, start with Quentin Tarantino’s movies in Column 1, put the cast of Once Upon a Time in Hollywood in Column 2, then put Brad Pitt’s entire filmography in Column 3. Keep going as long as you want, building a "chain" ala Six Degrees of Kevin Bacon.<p>I was frustrated that all popular movie websites are page-oriented: one HTML page per movie or person. I asked myself what a movie site designed in 2026 would look like, in an era when full-screen canvas sites like Miro are common. And then asked what if the site was built on a game engine? I used PixiJS.<p>I ingested TMDB movie data into my own SQLite database head of time, so there are no external API calls at runtime. This was necessary because opening a board with 100's of columns would exceed rate limits. My read-only SQLite DB lives on a Fly volume, attached to my Fly machine. Most of the hard engineering was making the boards virtual, so we materialize only the columns currently visible. This keeps the site at 60Hz even on huge boards.<p>Some pre-made board:<p>2025 Oscar Winners:
<a href="https://movie-chain.com/boards/oscars-2025" rel="nofollow">https://movie-chain.com/boards/oscars-2025</a><p>All of Christopher Nolan's movies:
<a href="https://movie-chain.com/boards/christopher-nolan" rel="nofollow">https://movie-chain.com/boards/christopher-nolan</a><p>Top movies of 1999:
<a href="https://movie-chain.com/boards/top-rated-1999" rel="nofollow">https://movie-chain.com/boards/top-rated-1999</a><p>Experience using Claude Code to build the site:
<a href="https://tobeva.com/articles/chess-simul/" rel="nofollow">https://tobeva.com/articles/chess-simul/</a></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47298005">https://news.ycombinator.com/item?id=47298005</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 08 Mar 2026 15:17:00 +0000</pubDate><link>https://movie-chain.com/</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=47298005</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47298005</guid></item><item><title><![CDATA[Coding with agents feels like a chess simul]]></title><description><![CDATA[
<p>Article URL: <a href="https://tobeva.com/articles/chess-simul/">https://tobeva.com/articles/chess-simul/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47234670">https://news.ycombinator.com/item?id=47234670</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 03 Mar 2026 16:17:52 +0000</pubDate><link>https://tobeva.com/articles/chess-simul/</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=47234670</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47234670</guid></item><item><title><![CDATA[Five Hundred PRs with Claude Code and the Future of Software Engineering]]></title><description><![CDATA[
<p>Article URL: <a href="https://tobeva.com/articles/five-hundred/">https://tobeva.com/articles/five-hundred/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47207087">https://news.ycombinator.com/item?id=47207087</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 01 Mar 2026 14:35:31 +0000</pubDate><link>https://tobeva.com/articles/five-hundred/</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=47207087</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47207087</guid></item><item><title><![CDATA[The Agentic Simul: What 500 PRs in two months taught me]]></title><description><![CDATA[
<p>Article URL: <a href="https://tobeva.com/articles/simul/">https://tobeva.com/articles/simul/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47167922">https://news.ycombinator.com/item?id=47167922</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 26 Feb 2026 16:06:46 +0000</pubDate><link>https://tobeva.com/articles/simul/</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=47167922</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47167922</guid></item><item><title><![CDATA[The Agentic Simul]]></title><description><![CDATA[
<p>Article URL: <a href="https://tobeva.com/articles/simul/">https://tobeva.com/articles/simul/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47156640">https://news.ycombinator.com/item?id=47156640</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 25 Feb 2026 19:35:05 +0000</pubDate><link>https://tobeva.com/articles/simul/</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=47156640</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47156640</guid></item><item><title><![CDATA[I Contain Multitudes: The Agentic Coding Simul]]></title><description><![CDATA[
<p>Article URL: <a href="https://tobeva.com/articles/multitudes/">https://tobeva.com/articles/multitudes/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47142679">https://news.ycombinator.com/item?id=47142679</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 24 Feb 2026 20:41:25 +0000</pubDate><link>https://tobeva.com/articles/multitudes/</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=47142679</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47142679</guid></item><item><title><![CDATA[New comment by pbw in "How to code Claude Code in 200 lines of code"]]></title><description><![CDATA[
<p>I have mixed feelings about the "Do X in N lines of code" genre. I applaud people taking the time to boil something down to its very essence, and implement just that, but I feel like the tone is always, "and the full thing is lame because it's so big," which seems off to me.</p>
]]></description><pubDate>Fri, 09 Jan 2026 02:46:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=46549531</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=46549531</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46549531</guid></item><item><title><![CDATA[New comment by pbw in "Total monthly number of StackOverflow questions over time"]]></title><description><![CDATA[
<p>SO was built to disrupt the marriage of Google and Experts Exchange. EE was using dark patterns to sucker unsuspecting users into paying for access to a crappy Q&A service. SO wildly succeeded, but almost 20 years later the world is very different.</p>
]]></description><pubDate>Sun, 04 Jan 2026 00:45:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=46483524</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=46483524</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46483524</guid></item><item><title><![CDATA[New comment by pbw in "Show HN: Gemini Pro 3 imagines the HN front page 10 years from now"]]></title><description><![CDATA[
<p>Gary Marcus, ha! He's generally not entirely wrong, but boy, is he annoying.</p>
]]></description><pubDate>Tue, 09 Dec 2025 20:54:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=46210525</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=46210525</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46210525</guid></item><item><title><![CDATA[New comment by pbw in "Horses: AI progress is steady. Human equivalence is sudden"]]></title><description><![CDATA[
<p>This is food for thought, but horses were a commodity; people are very much not interchangeable with each other. The BLS tracks ~1,000 different occupations. Each will fall to AI at a slightly different rate, and within each, there will be variations as well. But this doesn't mean it won't still subjectively happen "fast".</p>
]]></description><pubDate>Tue, 09 Dec 2025 02:13:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=46200496</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=46200496</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46200496</guid></item><item><title><![CDATA[New comment by pbw in "Netflix’s AV1 Journey: From Android to TVs and Beyond"]]></title><description><![CDATA[
<p>There's an HDR war brewing on TikTok and other social apps. A fraction of posts that use HDR are just massively brighter than the rest; the whole video shines like a flashlight. The apps are eventually going to have to detect HDR abuse.</p>
]]></description><pubDate>Fri, 05 Dec 2025 00:54:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=46155514</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=46155514</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46155514</guid></item><item><title><![CDATA[The Futile Quest for Artificial Intelligence (2006)]]></title><description><![CDATA[
<p>Article URL: <a href="https://archive.skeptic.com/archive/reading_room/artificial-intelligence-gone-awry/">https://archive.skeptic.com/archive/reading_room/artificial-intelligence-gone-awry/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46093336">https://news.ycombinator.com/item?id=46093336</a></p>
<p>Points: 5</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 30 Nov 2025 03:24:22 +0000</pubDate><link>https://archive.skeptic.com/archive/reading_room/artificial-intelligence-gone-awry/</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=46093336</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46093336</guid></item><item><title><![CDATA[New comment by pbw in "Beads – A memory upgrade for your coding agent"]]></title><description><![CDATA[
<p>Whether this exact approach catches on or not, it's turning the corner from "teaching AIs to develop using tools that were designed for humans" to "inventing new tools and techniques that are designed specifically for AI use". This makes sense because AIs are not human; they have different strengths and limitations.</p>
]]></description><pubDate>Fri, 28 Nov 2025 15:02:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=46079238</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=46079238</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46079238</guid></item><item><title><![CDATA[New comment by pbw in "Workday to acquire Pipedream"]]></title><description><![CDATA[
<p>Workday is a disaster, at least the version we have.</p>
]]></description><pubDate>Thu, 20 Nov 2025 00:55:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=45987403</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=45987403</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45987403</guid></item><item><title><![CDATA[New comment by pbw in "Die shots of as many CPUs and other interesting chips as possible"]]></title><description><![CDATA[
<p>To capture the individual transistors on a modern CPU, you'd need an image tens of terabytes in size, and it'd have to be captured by an electron microscope, not an optical image. And even that wouldn't let you see all the layers. Some of the very old CPUs, I'm not sure what resolution would be required.</p>
]]></description><pubDate>Wed, 22 Oct 2025 13:35:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=45668932</link><dc:creator>pbw</dc:creator><comments>https://news.ycombinator.com/item?id=45668932</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45668932</guid></item></channel></rss>