<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: sim04ful</title><link>https://news.ycombinator.com/user?id=sim04ful</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 18 Nov 2026 03:52:04 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=sim04ful" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Show HN: Logo Breeder]]></title><description><![CDATA[
<p>Article URL: <a href="https://simdijinkins.com/logobreeder/">https://simdijinkins.com/logobreeder/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50472066">https://news.ycombinator.com/item?id=50472066</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 12 Nov 2026 18:40:46 +0000</pubDate><link>https://simdijinkins.com/logobreeder/</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=50472066</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50472066</guid></item><item><title><![CDATA[New comment by sim04ful in "AlphaProof Code"]]></title><description><![CDATA[
<p>Curious question, in this case for verification they ported the software into a formal mathematical model. Why can't software development start from the other end instead ? Start with a formal model with the properties you want, then translate it into software.</p>
]]></description><pubDate>Tue, 10 Nov 2026 13:12:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=50439832</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=50439832</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50439832</guid></item><item><title><![CDATA[New comment by sim04ful in "How accurately did science fiction stories predict AI?"]]></title><description><![CDATA[
<p>Neal Stephenson's Diamond Age (a young lady's illustrated primer) ≈ LLMs + Intelligent UI (OpenAI)</p>
]]></description><pubDate>Fri, 06 Nov 2026 06:32:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=50388911</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=50388911</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50388911</guid></item><item><title><![CDATA[New comment by sim04ful in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>I've been increasingly interested in language-oriented programming and denotational design. So i get claude to create a domain specific language in Racket modelling the software i'm trying to build, we create nouns and verbs whose meaning fits the behaviour i'm going for, then when we find bugs or notice we need more exceptional (less-elegant) one-off behaviour to tackle edge-cases, we iterate on the language in such a manner that it these are tackled emergently with preferably less concepts, more cohersion and composition. It's somewhat similar to how memory safety is handled at compile time in Rust but for business logic.</p>
]]></description><pubDate>Wed, 04 Nov 2026 16:28:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=50367941</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=50367941</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50367941</guid></item><item><title><![CDATA[New comment by sim04ful in "Patrick Stewart has died"]]></title><description><![CDATA[
<p>His performance in TNG was so great it left such an impression on adult me. So much so I tend to end my AI agent approvals with "Make it so number 1"</p>
]]></description><pubDate>Thu, 29 Oct 2026 20:19:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=50295250</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=50295250</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50295250</guid></item><item><title><![CDATA[New comment by sim04ful in "MacBook Pro with PROLED XDR Display and Touch"]]></title><description><![CDATA[
<p>well put!</p>
]]></description><pubDate>Wed, 28 Oct 2026 18:13:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=50278355</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=50278355</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50278355</guid></item><item><title><![CDATA[New comment by sim04ful in "MacBook Pro with PROLED XDR Display and Touch"]]></title><description><![CDATA[
<p>There's no universe this doesn't negatively affect the UX of the OS for non-touch users. You can't simply support (or rather you can half-arse) new affordances without contorting the rest of the already well worn paths.</p>
]]></description><pubDate>Wed, 28 Oct 2026 17:25:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=50277273</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=50277273</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50277273</guid></item><item><title><![CDATA[Denotation Design]]></title><description><![CDATA[
<p>Article URL: <a href="https://reasonablypolymorphic.com/blog/follow-the-denotation/">https://reasonablypolymorphic.com/blog/follow-the-denotation/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50224184">https://news.ycombinator.com/item?id=50224184</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 24 Oct 2026 19:16:08 +0000</pubDate><link>https://reasonablypolymorphic.com/blog/follow-the-denotation/</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=50224184</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50224184</guid></item><item><title><![CDATA[New comment by sim04ful in "The Decoherence Trap"]]></title><description><![CDATA[
<p>Excellent article. This incoherence is a side-effect of a system built far faster than it is consolidated and thought about from an external behavioral standpoint.
I've created a skill that the agent runs after significant codebase work has been done: <a href="https://gist.github.com/scroobius-pip/adb87dffca64b11bad3dd1d21b163895" rel="nofollow">https://gist.github.com/scroobius-pip/adb87dffca64b11bad3dd1...</a></p>
]]></description><pubDate>Wed, 21 Oct 2026 12:04:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=50179500</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=50179500</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50179500</guid></item><item><title><![CDATA[New comment by sim04ful in "Court throws out killer's sentence after judge said he loved AI video of victim"]]></title><description><![CDATA[
<p>Not so much perplexing if they considered the AI rendition an accurate representation. It's somewhat quite internally consistent in its own illogical way</p>
]]></description><pubDate>Fri, 09 Oct 2026 14:43:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=50021227</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=50021227</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50021227</guid></item><item><title><![CDATA[New comment by sim04ful in "Dust: Pretraining Transformers Without Backpropagation"]]></title><description><![CDATA[
<p>For me credit assignment without a global clock is extremely important, i believe it's a necessary step towards end to end training of models In-materio.</p>
]]></description><pubDate>Tue, 06 Oct 2026 07:17:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=49975262</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=49975262</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49975262</guid></item><item><title><![CDATA[New comment by sim04ful in "Ask HN: What are you reading?"]]></title><description><![CDATA[
<p>Samuel Butler's adaptation of Homer.</p>
]]></description><pubDate>Tue, 29 Sep 2026 16:35:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=49896123</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=49896123</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49896123</guid></item><item><title><![CDATA[New comment by sim04ful in "Malleable software: Restoring user agency in a world of locked-down apps (2025)"]]></title><description><![CDATA[
<p>I've been thinking about this issue. One thing i realized early on is that the presentation layer is transcient it doesn't matter as much as data representation and storage.</p>
]]></description><pubDate>Mon, 28 Sep 2026 06:57:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=49874496</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=49874496</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49874496</guid></item><item><title><![CDATA[New comment by sim04ful in "Tells of a Slop UI"]]></title><description><![CDATA[
<p>The one thing that vexxes me up so much is the model bring up internal decisions in consumer facing views.</p>
]]></description><pubDate>Sun, 27 Sep 2026 16:16:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=49868047</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=49868047</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49868047</guid></item><item><title><![CDATA[New comment by sim04ful in "Kev: Tiny Jev-like family of decision models built on top of Qwen3.5"]]></title><description><![CDATA[
<p>Hi, I'm currently planning on launching a product like this "Grammarly for Design" in a few weeks. Would you be interested in being part of the alpha group ?</p>
]]></description><pubDate>Mon, 21 Sep 2026 09:34:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=49785073</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=49785073</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49785073</guid></item><item><title><![CDATA[New comment by sim04ful in "OpenJev"]]></title><description><![CDATA[
<p>This is a problem that i'm actively working on (<a href="https://fudge.design" rel="nofollow">https://fudge.design</a>), what i've realised is that it's simply not an issue of capability - given a well crafted site and a competently written visually aware harness, most recent models can replicate that website.<p>So it's what lies between saying "I want x website" -[.....] -> Code+Assets<p>The issue has to do with specification fidelity, in short a grill-me style aesthetic interrogation using illustrative tooling - ascii diagrams for specifying layout, copy and user-flow, image-gen mockups for higher fidelity mockups. References are also very important for nailing down the aesthetical qualities. I've noticed it's far better vs purely text description to simply gather up a mood-board telling the llm to find commonalities and come up with a design system and brand guide.<p>So I don't believe it's an unsolvable problem, it's simply a lack of effort on the implementors part. Also there's probably some survivor's bias here (you won't notice an intentionally designed vibe-coded site)<p>For example here's one reference exploration site i recently made with grok: <a href="https://explorer.withfudge.com/" rel="nofollow">https://explorer.withfudge.com/</a></p>
]]></description><pubDate>Fri, 18 Sep 2026 11:40:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=49752940</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=49752940</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49752940</guid></item><item><title><![CDATA[New comment by sim04ful in "Introducing System One Models and Jev"]]></title><description><![CDATA[
<p>This sort of stuff almost sends shivers down my spine, it's like i'm looking 5 years into the future.</p>
]]></description><pubDate>Tue, 15 Sep 2026 19:59:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=49718047</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=49718047</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49718047</guid></item><item><title><![CDATA[New comment by sim04ful in "Ask HN: What are you working on? (September 2026)"]]></title><description><![CDATA[
<p><a href="https://fudge.design" rel="nofollow">https://fudge.design</a> 
Gives AI agents better design taste by enabling them search for references.</p>
]]></description><pubDate>Mon, 14 Sep 2026 06:33:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=49692757</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=49692757</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49692757</guid></item><item><title><![CDATA[Language Oriented Programming (1994) [pdf]]]></title><description><![CDATA[
<p>Article URL: <a href="https://john.cs.olemiss.edu/~hcc/csci450/notes/localcopy/LanguageOrientedProgramming.pdf">https://john.cs.olemiss.edu/~hcc/csci450/notes/localcopy/LanguageOrientedProgramming.pdf</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49672394">https://news.ycombinator.com/item?id=49672394</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 12 Sep 2026 14:00:26 +0000</pubDate><link>https://john.cs.olemiss.edu/~hcc/csci450/notes/localcopy/LanguageOrientedProgramming.pdf</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=49672394</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49672394</guid></item><item><title><![CDATA[New comment by sim04ful in "A misalignment of AI in mathematics"]]></title><description><![CDATA[
<p>Playing a devil's advocate. Why do we need understanding ? To take an example i would say ~99% of the population do not understand how combustion engines or how semiconductors work, what say another 1% ?
Is the fear post-apocalyptic in nature ? We need some human priesthood to carry on tradition ? why ?<p>Let's assume in the next decade GPT-7 PRO Ultra is cheaply ubiquitous, inspectable, reproducible, transferable, reasonably un-constrained by any institutional interests.<p>What say the 1% ?<p><i>Lifted up my comment for addition visibility</i></p>
]]></description><pubDate>Fri, 11 Sep 2026 19:51:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=49664390</link><dc:creator>sim04ful</dc:creator><comments>https://news.ycombinator.com/item?id=49664390</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49664390</guid></item></channel></rss>