<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: lgrapenthin</title><link>https://news.ycombinator.com/user?id=lgrapenthin</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 24 Sep 2026 18:50:19 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=lgrapenthin" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by lgrapenthin in "Building an Advanced Agentic Harness"]]></title><description><![CDATA[
<p>Because its all moonshining.<p>Trying to make gold from pyrite.</p>
]]></description><pubDate>Wed, 05 Aug 2026 15:43:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=49184486</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=49184486</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49184486</guid></item><item><title><![CDATA[New comment by lgrapenthin in "A Road to Lisp: Which Lisp"]]></title><description><![CDATA[
<p>Choose any LISP, and the right LISP will choose you.</p>
]]></description><pubDate>Fri, 17 Jul 2026 18:50:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=48950912</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=48950912</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48950912</guid></item><item><title><![CDATA[New comment by lgrapenthin in "After 7 years in production, Scarf has reluctantly moved away from Haskell"]]></title><description><![CDATA[
<p>tldr; they decided to sacrifice quality for quantity via outsourcing their programming, and find Python more suitable for this.<p>Which it always has been, whether  outsourcing to cheap "talent" overseas, or now a subscription service text generator.</p>
]]></description><pubDate>Sat, 11 Jul 2026 16:40:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=48873507</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=48873507</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48873507</guid></item><item><title><![CDATA[New comment by lgrapenthin in "The best response to AI slop and online noise is from Robin Williams"]]></title><description><![CDATA[
<p>Not a day passes with my LLM of choice making completely baseless claims about "many people", who supposedly share all my problems and solve them like the LLM proposes</p>
]]></description><pubDate>Sun, 28 Jun 2026 03:38:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=48704097</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=48704097</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48704097</guid></item><item><title><![CDATA[New comment by lgrapenthin in "Lisp in the Rust Type System"]]></title><description><![CDATA[
<p>"Here is the X part", a commonly generated attention catcher these days, combined with an expert level fact, compacted into casual tone. Note it does not state opinion or reports subjective experience, which alltogether makes it a somewhat unfailable "Did you know?" addition.
It is easy to mass generate such commentary and you can frequently find it on Twitter, too.<p>I find it hard to believe that a human would after reading this article make the stated observation, and then write this exact comment.</p>
]]></description><pubDate>Mon, 22 Jun 2026 17:11:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=48632908</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=48632908</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48632908</guid></item><item><title><![CDATA[New comment by lgrapenthin in "Lisp in the Rust Type System"]]></title><description><![CDATA[
<p>did you generate this comment?</p>
]]></description><pubDate>Mon, 22 Jun 2026 11:39:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=48628815</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=48628815</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48628815</guid></item><item><title><![CDATA[New comment by lgrapenthin in "My thoughts after using Clojure for about a month"]]></title><description><![CDATA[
<p>"As a rule of thumb, if your application never has 10,000 virtual threads or more, it is unlikely to benefit from virtual threads."<p><a href="https://docs.oracle.com/en/java/javase/21/core/virtual-threads.html" rel="nofollow">https://docs.oracle.com/en/java/javase/21/core/virtual-threa...</a></p>
]]></description><pubDate>Wed, 03 Jun 2026 02:14:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=48379038</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=48379038</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48379038</guid></item><item><title><![CDATA[New comment by lgrapenthin in "My thoughts after using Clojure for about a month"]]></title><description><![CDATA[
<p>Clojure is about its rigorous and pragmatic "immutability first" paradigm that you simply don't get from other PLs.<p>LISP is much more than just a runtime syntax, such as its distinct evaluation model and metalinguistic core.<p>The JVM was chosen for Clojure because of its reach and vast ecosystem.  People have ported Clojure to other runtimes, even Beam (Clojerl), where it enjoys decent success, too.</p>
]]></description><pubDate>Wed, 03 Jun 2026 02:08:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=48378997</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=48378997</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48378997</guid></item><item><title><![CDATA[New comment by lgrapenthin in "I'm Tired of Talking to AI"]]></title><description><![CDATA[
<p>Why does this read like written by AI?</p>
]]></description><pubDate>Wed, 27 May 2026 17:51:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=48297870</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=48297870</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48297870</guid></item><item><title><![CDATA[New comment by lgrapenthin in "We stopped AI bot spam in our GitHub repo using Git's –author flag"]]></title><description><![CDATA[
<p>What you are describing is exactly a security implication.</p>
]]></description><pubDate>Mon, 18 May 2026 16:30:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=48181953</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=48181953</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48181953</guid></item><item><title><![CDATA[New comment by lgrapenthin in "Clojurists Together – Q2 2026 Open Source Funding Announcement"]]></title><description><![CDATA[
<p>Might be some personal beef, but I don't know really and don't care enough.  He makes these authorative claims mixed with personal sentiment and then doesn't back them up.<p>Here for instance the core team supposedly has "lost control of the compiler" 
<a href="https://x.com/dustingetz/status/1947643515480965346" rel="nofollow">https://x.com/dustingetz/status/1947643515480965346</a><p>Work on the compiler had been pushed a month earlier <a href="https://github.com/clojure/clojure/commit/6a3e0f02c6a96fcef2789e5da0bb80cd65405c03" rel="nofollow">https://github.com/clojure/clojure/commit/6a3e0f02c6a96fcef2...</a></p>
]]></description><pubDate>Tue, 05 May 2026 10:16:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=48020422</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=48020422</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48020422</guid></item><item><title><![CDATA[New comment by lgrapenthin in "Clojurists Together – Q2 2026 Open Source Funding Announcement"]]></title><description><![CDATA[
<p>Of course calling out baseless FUD is helpful.  Otherwise it just discourages people from engaging with Clojure, which is not helpful.</p>
]]></description><pubDate>Tue, 05 May 2026 00:18:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=48016590</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=48016590</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48016590</guid></item><item><title><![CDATA[New comment by lgrapenthin in "Clojurists Together – Q2 2026 Open Source Funding Announcement"]]></title><description><![CDATA[
<p>There is no falling apart.  This guy just tries to spread this narrative every two months or so, idky.  Check out latest dev call <a href="https://www.youtube.com/watch?v=ngyvDkZA3o0" rel="nofollow">https://www.youtube.com/watch?v=ngyvDkZA3o0</a></p>
]]></description><pubDate>Mon, 04 May 2026 11:14:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=48007195</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=48007195</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48007195</guid></item><item><title><![CDATA[New comment by lgrapenthin in "Agentic Coding Is a Trap"]]></title><description><![CDATA[
<p>Indeed.  Generated code is also harder to read because it violates all semantic expectations that rely on the mental model of a human author.  A generated piece of code is linguistically plausible but often unknowingly imitates common idioms so incoherently that the actual bug may be accidentally disguised in a way no sane human (even a bad programmer) could have come up with.<p>Since LLMs have no internal evaluation, as a reviewer one has to account for it and evaluate line by line, rebuild from scratch any hidden rationale and tacit knowledge the LLM didn't have in the first place - only to be mislead into non concerns draining costly hours.<p>At this point, the investment is often deeper than writing from scratch.</p>
]]></description><pubDate>Mon, 04 May 2026 02:29:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=48003975</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=48003975</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48003975</guid></item><item><title><![CDATA[New comment by lgrapenthin in "Why I still reach for Lisp and Scheme instead of Haskell"]]></title><description><![CDATA[
<p>In Clojure<p><pre><code>    true: true
    false: false
    null: nil
    []: []
    {}: {}</code></pre></p>
]]></description><pubDate>Thu, 30 Apr 2026 13:36:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=47962233</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=47962233</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47962233</guid></item><item><title><![CDATA[New comment by lgrapenthin in "System Card: Claude Mythos Preview [pdf]"]]></title><description><![CDATA[
<p>They are just trying to peddle their "It's alive" headlines.<p>Text generators mostly generate the text their are trained and asked to generate, and asking it to run a vending machine, having it write blog posts under fictional living computer identity, or now calling it "Mythos" - its all just marketing.</p>
]]></description><pubDate>Wed, 08 Apr 2026 19:00:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=47694691</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=47694691</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47694691</guid></item><item><title><![CDATA[New comment by lgrapenthin in "Common Lisp Screenshots: today's CL applications in action"]]></title><description><![CDATA[
<p>Assuming that everybody disagreeing with such takes simply can't have tried the latest generator is quite telling.  Consider, that maybe, I'm not as easily impressed?</p>
]]></description><pubDate>Sat, 14 Feb 2026 16:25:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=47015762</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=47015762</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47015762</guid></item><item><title><![CDATA[New comment by lgrapenthin in "Common Lisp Screenshots: today's CL applications in action"]]></title><description><![CDATA[
<p>My hammer is also solving problems.  Still, hammering is not programming.  LLMs are text generators.</p>
]]></description><pubDate>Sat, 14 Feb 2026 06:43:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=47012234</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=47012234</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47012234</guid></item><item><title><![CDATA[New comment by lgrapenthin in "Common Lisp Screenshots: today's CL applications in action"]]></title><description><![CDATA[
<p>You are comparing a PL to a text generator.  What are you on?</p>
]]></description><pubDate>Sat, 14 Feb 2026 04:08:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=47011468</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=47011468</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47011468</guid></item><item><title><![CDATA[New comment by lgrapenthin in "Ex-GitHub CEO launches a new developer platform for AI agents"]]></title><description><![CDATA[
<p>The negativity is driven by outrageous claims how AIs will replace programmers, or how english is the PL of the future.
T</p>
]]></description><pubDate>Wed, 11 Feb 2026 18:07:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=46978512</link><dc:creator>lgrapenthin</dc:creator><comments>https://news.ycombinator.com/item?id=46978512</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46978512</guid></item></channel></rss>