<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: blueblazin</title><link>https://news.ycombinator.com/user?id=blueblazin</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 15 Jun 2026 10:50:41 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=blueblazin" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by blueblazin in "Formal methods and the future of programming"]]></title><description><![CDATA[
<p>As someone with a bit of interest in programming languages (design and implementation) this was really interesting to me:<p>> For most people who work on programming languages, the easy part is coming up with new and better ideas about how to make programming better. The hard part is convincing anyone to actually use those ideas for real work.<p>Totally agree, there's only so much strangeness you can introduce in a new language[1] regardless of benefit.<p>But AI agents should not feel much resistance to radically new ideas in PL design. I've been thinking for a while now about how PL design will evolve post agentic AI. I think it will be very interesting to see what new ideas we can come up with to improve programming languages when we worry much less about adoption.<p>[1] <a href="https://steveklabnik.com/writing/the-language-strangeness-budget/" rel="nofollow">https://steveklabnik.com/writing/the-language-strangeness-bu...</a></p>
]]></description><pubDate>Mon, 15 Jun 2026 09:54:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=48538985</link><dc:creator>blueblazin</dc:creator><comments>https://news.ycombinator.com/item?id=48538985</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48538985</guid></item><item><title><![CDATA[New comment by blueblazin in "Claude Opus 4.8"]]></title><description><![CDATA[
<p>I think they poison outputs now if they detect distillation attempts. So a model trained on distilled outputs will be stupider.</p>
]]></description><pubDate>Fri, 29 May 2026 12:57:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=48322512</link><dc:creator>blueblazin</dc:creator><comments>https://news.ycombinator.com/item?id=48322512</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48322512</guid></item><item><title><![CDATA[New comment by blueblazin in "Show HN: Game Boy pixel pipeline explorer"]]></title><description><![CDATA[
<p>Thanks for the kind words! Even though this is definitely meant for desktop screens, I really didn't want it to fall apart on mobile. As for upvotes, it's super niche so I wasn't really expecting even a single one tbh</p>
]]></description><pubDate>Thu, 28 May 2026 12:21:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=48307895</link><dc:creator>blueblazin</dc:creator><comments>https://news.ycombinator.com/item?id=48307895</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48307895</guid></item><item><title><![CDATA[Show HN: Game Boy pixel pipeline explorer]]></title><description><![CDATA[
<p>I made a pixel pipeline explorer for the original Game Boy's Pixel Processing Unit (PPU). If you are implementing a Game Boy emulator or just interested in it then this might provide some help :)</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48293674">https://news.ycombinator.com/item?id=48293674</a></p>
<p>Points: 14</p>
<p># Comments: 6</p>
]]></description><pubDate>Wed, 27 May 2026 13:04:23 +0000</pubDate><link>https://pixelpipeline.xyz</link><dc:creator>blueblazin</dc:creator><comments>https://news.ycombinator.com/item?id=48293674</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48293674</guid></item><item><title><![CDATA[New comment by blueblazin in "Ask HN: What Are You Working On? (March 2026)"]]></title><description><![CDATA[
<p>A fully vibe coded python 3.14 interpreter in Rust: <a href="https://blueblazin.github.io/pyrs" rel="nofollow">https://blueblazin.github.io/pyrs</a><p>Now at 350k lines. Native and wasm binaries (you can try the limited wasm version online). Currently adding a full CPython test suite benchmark.<p>Just for fun, not trying to replace CPython here. Mainly to test the limits of current coding agents.</p>
]]></description><pubDate>Mon, 09 Mar 2026 03:12:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=47304478</link><dc:creator>blueblazin</dc:creator><comments>https://news.ycombinator.com/item?id=47304478</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47304478</guid></item><item><title><![CDATA[Show HN: AI agent coded Python 3.14 interpreter in Rust]]></title><description><![CDATA[
<p>Hi HN, inspired by the Cursor team's attempt to use agents to vibe code a browser, I decided to try something a bit easier but still challenging enough to push the limits of current coding agents.<p>The result is a Python 3.14 targeting python interpreter written in Rust entirely by a single coding agent (Codex) in 30 days.<p>While the main focus is a native interpreter (macOS and linux atm) there is also a limited-functionality WASM version that you can try immediately on the website!<p>This was purely a fun project and I certainly had a lot of fun. My main role was playing pretend technical program manager and trying to prevent the agent from derailing (which it did very regularly). But anyway, 30 days, 342k lines of code, and nearly 2000 commits later, I have something that works.<p>I thought I'd be done in 3-5 days, then 2 weeks, then 3, before it was ready after 30 days. Feel like I've learned a lot more about these strange, impressive, and frustrating creatures that are agentic coding models as well.<p>Still a long way to go, and I will also be adding some performance benchmarks and test results in the coming days, but there it is.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47274804">https://news.ycombinator.com/item?id=47274804</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 06 Mar 2026 13:44:04 +0000</pubDate><link>https://blueblazin.github.io/pyrs/</link><dc:creator>blueblazin</dc:creator><comments>https://news.ycombinator.com/item?id=47274804</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47274804</guid></item><item><title><![CDATA[New comment by blueblazin in "I’m joining OpenAI"]]></title><description><![CDATA[
<p>As I understand Peter had already early retired because of a successful startup exit and presumably has more money than he knows what to do with. Does that help make you feel less jealous on him getting a job at oai?</p>
]]></description><pubDate>Mon, 16 Feb 2026 11:24:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=47033746</link><dc:creator>blueblazin</dc:creator><comments>https://news.ycombinator.com/item?id=47033746</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47033746</guid></item><item><title><![CDATA[Vibe coding a Game Boy emulator]]></title><description><![CDATA[
<p>Article URL: <a href="https://sanjeetnd.com/vibecoding-gameboy">https://sanjeetnd.com/vibecoding-gameboy</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44647334">https://news.ycombinator.com/item?id=44647334</a></p>
<p>Points: 5</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 22 Jul 2025 14:28:14 +0000</pubDate><link>https://sanjeetnd.com/vibecoding-gameboy</link><dc:creator>blueblazin</dc:creator><comments>https://news.ycombinator.com/item?id=44647334</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44647334</guid></item><item><title><![CDATA[An implementation of a subset of JavaScript in that subset of JavaScript]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/BlueBlazin/thislang">https://github.com/BlueBlazin/thislang</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=27983036">https://news.ycombinator.com/item?id=27983036</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 28 Jul 2021 12:40:41 +0000</pubDate><link>https://github.com/BlueBlazin/thislang</link><dc:creator>blueblazin</dc:creator><comments>https://news.ycombinator.com/item?id=27983036</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=27983036</guid></item></channel></rss>