<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: Vgoose</title><link>https://news.ycombinator.com/user?id=Vgoose</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 21 Oct 2026 09:17:11 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=Vgoose" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by Vgoose in "No country for mediocre mathematicians"]]></title><description><![CDATA[
<p>I wish I could write this well. What an enjoyable read.</p>
]]></description><pubDate>Mon, 31 Aug 2026 19:23:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=49513828</link><dc:creator>Vgoose</dc:creator><comments>https://news.ycombinator.com/item?id=49513828</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49513828</guid></item><item><title><![CDATA[Types with AI: Working with LLMs Through Types]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.alecvo.org/blog/types-with-ai/">https://www.alecvo.org/blog/types-with-ai/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49144719">https://news.ycombinator.com/item?id=49144719</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 02 Aug 2026 13:52:12 +0000</pubDate><link>https://www.alecvo.org/blog/types-with-ai/</link><dc:creator>Vgoose</dc:creator><comments>https://news.ycombinator.com/item?id=49144719</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49144719</guid></item><item><title><![CDATA[New comment by Vgoose in "Benchmarking Opus 5 on SlopCodeBench"]]></title><description><![CDATA[
<p>I think there's a simple explanation for why the models aren't good at "maintainable" code: they're not explicitly trained on it in post-training. It being hard to quantify what maintainable is and there not being a popular benchmark for maintainability are probably some reasons why.</p>
]]></description><pubDate>Wed, 29 Jul 2026 02:00:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=49092585</link><dc:creator>Vgoose</dc:creator><comments>https://news.ycombinator.com/item?id=49092585</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49092585</guid></item><item><title><![CDATA[New comment by Vgoose in "Benchmarking Opus 5 on SlopCodeBench"]]></title><description><![CDATA[
<p>Thanks for sharing, I've never heard of variety before and that was an interesting read. It makes me think of a broader term I've been using to describe the run time state of the system: Entropy. I've given up on measuring that for now and I'm settling for a compile time proxy through measuring the _semantic_ cardinality of types as this seems a bit more approachable for a POC.<p>One drawback I ran into was that the variety/entropy of scalars tends to dominate everything else. I'm clamping them to 1 for now but that's also not great as it punishes more descriptive systems.</p>
]]></description><pubDate>Wed, 29 Jul 2026 01:42:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=49092429</link><dc:creator>Vgoose</dc:creator><comments>https://news.ycombinator.com/item?id=49092429</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49092429</guid></item><item><title><![CDATA[New comment by Vgoose in "Benchmarking Opus 5 on SlopCodeBench"]]></title><description><![CDATA[
<p>Ive have a definition of state space that is calculated by just the types of the system. It’s a rough approximation of the true state space but it’s convenient (and more reflective of what we actually mean by system state IMO) and types are inherently accessible to the model. I recently put down some thoughts around working with types to improve communication w/ AI that kind of sets this framing up: <a href="https://www.alecvo.org/blog/types-with-ai/" rel="nofollow">https://www.alecvo.org/blog/types-with-ai/</a>. The actual definition is still WIP.</p>
]]></description><pubDate>Tue, 28 Jul 2026 13:49:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=49083875</link><dc:creator>Vgoose</dc:creator><comments>https://news.ycombinator.com/item?id=49083875</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49083875</guid></item><item><title><![CDATA[New comment by Vgoose in "Benchmarking Opus 5 on SlopCodeBench"]]></title><description><![CDATA[
<p>Nice! I actually ran across this paper+benchmark recently, too. It's the first I've found that start to aim at some of the non-functional and longitudinal requirements that I think have always been an important part of writing production code.<p>It's especially relevant now that models are good enough to solve ~most point-in-time problems.<p>Some relevant but disconnected thoughts:<p>- deterministic scores are so nice<p>- what "maintainable" is is probably some high dimensional space described by these signals; it'd probably require some human labeling to figure out where this space is<p>- another signal I've been thinking about and I'm seeing increasingly get brought up is the state space of a system; I'm seeing formal methods pop up a lot recently</p>
]]></description><pubDate>Tue, 28 Jul 2026 00:40:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=49077756</link><dc:creator>Vgoose</dc:creator><comments>https://news.ycombinator.com/item?id=49077756</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49077756</guid></item><item><title><![CDATA[Types with AI]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.alecvo.org/blog/types-with-ai/">https://www.alecvo.org/blog/types-with-ai/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49063256">https://news.ycombinator.com/item?id=49063256</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 26 Jul 2026 23:01:46 +0000</pubDate><link>https://www.alecvo.org/blog/types-with-ai/</link><dc:creator>Vgoose</dc:creator><comments>https://news.ycombinator.com/item?id=49063256</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49063256</guid></item><item><title><![CDATA[New comment by Vgoose in "Programming Is Mostly Thinking (2014)"]]></title><description><![CDATA[
<p>My architect introduced Architecture Decision Records to my company and it's made a world of difference. Are there other tools and mechanisms people have found helpful to facilitate and scale group thinking?</p>
]]></description><pubDate>Mon, 22 Apr 2024 21:44:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=40121430</link><dc:creator>Vgoose</dc:creator><comments>https://news.ycombinator.com/item?id=40121430</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40121430</guid></item><item><title><![CDATA[New comment by Vgoose in "The Unreasonable Effectiveness of Sequence Diagrams in MermaidJS"]]></title><description><![CDATA[
<p>This is my go to diagramming tool. It takes a lot of little tricks to get things to turn out exactly how you want, but they're not required. It communicates information just fine. The tricks are only required if you care about aesthetics.</p>
]]></description><pubDate>Mon, 24 Jul 2023 14:56:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=36849051</link><dc:creator>Vgoose</dc:creator><comments>https://news.ycombinator.com/item?id=36849051</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=36849051</guid></item><item><title><![CDATA[New comment by Vgoose in "Postman acquires Akita for automated API observability"]]></title><description><![CDATA[
<p>I've actually seen more of her name than Akita itself. In a way, that's great marketing.</p>
]]></description><pubDate>Wed, 19 Jul 2023 15:44:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=36788281</link><dc:creator>Vgoose</dc:creator><comments>https://news.ycombinator.com/item?id=36788281</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=36788281</guid></item><item><title><![CDATA[New comment by Vgoose in "Bootstrapping a multiplayer server with Elixir"]]></title><description><![CDATA[
<p>It used to be around every few weeks I would read something cool about Elixir. This past two weeks it's down to every few days.<p>I think someone's trying to tell me something.</p>
]]></description><pubDate>Thu, 29 Jul 2021 21:05:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=28001503</link><dc:creator>Vgoose</dc:creator><comments>https://news.ycombinator.com/item?id=28001503</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=28001503</guid></item></channel></rss>