<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: internet_points</title><link>https://news.ycombinator.com/user?id=internet_points</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 16 Nov 2026 01:05:19 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=internet_points" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by internet_points in "A technical vision for the Haskell ecosystem"]]></title><description><![CDATA[
<p>I find initial build to be the most annoying, since it stops me from starting new projects in Haskell. It's also very annoying when setting up CI or switching machines or introducing new team members.</p>
]]></description><pubDate>Sat, 14 Nov 2026 08:32:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=50495205</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50495205</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50495205</guid></item><item><title><![CDATA[New comment by internet_points in "A technical vision for the Haskell ecosystem"]]></title><description><![CDATA[
<p>Hm, I found writing FFI code from Haskell quite easy.<p>I've been meaning to try the new
<a href="https://well-typed.com/blog/2026/10/hs-bindgen-official-release/" rel="nofollow">https://well-typed.com/blog/2026/10/hs-bindgen-official-rele...</a> 
which looks even nicer, but haven't found a missing library yet to try it on :)</p>
]]></description><pubDate>Sat, 14 Nov 2026 08:24:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=50495167</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50495167</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50495167</guid></item><item><title><![CDATA[New comment by internet_points in "A technical vision for the Haskell ecosystem"]]></title><description><![CDATA[
<p>shell in the long tail? lol</p>
]]></description><pubDate>Sat, 14 Nov 2026 08:20:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=50495151</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50495151</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50495151</guid></item><item><title><![CDATA[New comment by internet_points in "A technical vision for the Haskell ecosystem"]]></title><description><![CDATA[
<p>My main takeaway from that post was that, apart from "don't use assembly", none of the experiments showed strong evidence either way, and the things that took time were when the agent got stuck doing silly things like invoking cargo with the wrong arguments. Ie. there's a lot of measurement noise, and not any strong signal, and "LLMs are good at generating $PL" isn't well-founded as an argument for picking $PL. So we're back to the old arguments for picking a language, like "I find it readable/enjoyable"</p>
]]></description><pubDate>Sat, 14 Nov 2026 08:19:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=50495142</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50495142</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50495142</guid></item><item><title><![CDATA[New comment by internet_points in "AI is destroying the trust between writers and readers"]]></title><description><![CDATA[
<p>> Amazon spends a lot of time and effort trying to prevent these [fake] books from getting posted,” Mary Rasenberger, the CEO of the Authors Guild, told me, “but it’s always a game of catch-up.”<p>Do they really? They take a cut; they have incentives to let people get scammed.</p>
]]></description><pubDate>Fri, 13 Nov 2026 15:03:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=50484580</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50484580</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50484580</guid></item><item><title><![CDATA[From action to static description–How AI changed Jørn Lier Horst's writing style]]></title><description><![CDATA[
<p>Article URL: <a href="https://jilltxt.net/from-action-to-static-descriptions-how-using-ai-to-write-with-changed-jorn-lier-horsts-style/">https://jilltxt.net/from-action-to-static-descriptions-how-using-ai-to-write-with-changed-jorn-lier-horsts-style/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50484412">https://news.ycombinator.com/item?id=50484412</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 13 Nov 2026 14:53:15 +0000</pubDate><link>https://jilltxt.net/from-action-to-static-descriptions-how-using-ai-to-write-with-changed-jorn-lier-horsts-style/</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50484412</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50484412</guid></item><item><title><![CDATA[New comment by internet_points in "Emacs in the Age of Magic"]]></title><description><![CDATA[
<p>ctrl+shift+r enables reader mode in firefox</p>
]]></description><pubDate>Fri, 13 Nov 2026 14:44:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=50484249</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50484249</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50484249</guid></item><item><title><![CDATA[New comment by internet_points in "ExcalidrawZ: Local Native Excalidraw on macOS/iOS"]]></title><description><![CDATA[
<p>already exists via emacs =P <a href="https://github.com/yibie/excali-mode" rel="nofollow">https://github.com/yibie/excali-mode</a></p>
]]></description><pubDate>Thu, 12 Nov 2026 17:05:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=50470545</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50470545</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50470545</guid></item><item><title><![CDATA[New comment by internet_points in "Space Mirrors Promise Daylight in the Dark, but Rescue Teams Aren't Convinced"]]></title><description><![CDATA[
<p>So the people involved in search and rescue said it would just get in the way, and might even be detrimental, and they already use night vision anyway.<p>But the people who would be paying for it said "it would definitely be something we would utilize […] But we have no idea what it would cost". (Is this just standard naive techno-optimisim, or are there some bedpartners we don't know about?)</p>
]]></description><pubDate>Mon, 09 Nov 2026 14:01:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=50425746</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50425746</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50425746</guid></item><item><title><![CDATA[Space Mirrors Promise Daylight in the Dark, but Rescue Teams Aren't Convinced]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.backpacker.com/news-and-events/news/space-mirrors-search-rescue-test/">https://www.backpacker.com/news-and-events/news/space-mirrors-search-rescue-test/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50425673">https://news.ycombinator.com/item?id=50425673</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 09 Nov 2026 13:57:08 +0000</pubDate><link>https://www.backpacker.com/news-and-events/news/space-mirrors-search-rescue-test/</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50425673</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50425673</guid></item><item><title><![CDATA[New comment by internet_points in "Software Line Specialist"]]></title><description><![CDATA[
<p>This is hilarious :-D<p>I clicked apply</p>
]]></description><pubDate>Fri, 06 Nov 2026 15:03:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=50393180</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50393180</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50393180</guid></item><item><title><![CDATA[New comment by internet_points in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>OP said "I'm curious how people on HN are using AI day to day" and I gave an honest answer. If the answers were only from those using agentic setups daily, that would give a skewed picture. (And I do have <i>some</i> experience with agentic coding, but for now I'm staying away from it; mainly because I don't trust it with my data and I can't quite justify the cost of a local setup.)<p>But before this thread gets too deep, maybe you want to ask  <a href="https://news.ycombinator.com/item?id=50376720">https://news.ycombinator.com/item?id=50376720</a> why they feel compelled to answer here. Or <a href="https://news.ycombinator.com/item?id=50375782">https://news.ycombinator.com/item?id=50375782</a> . Or <a href="https://news.ycombinator.com/item?id=50367460">https://news.ycombinator.com/item?id=50367460</a> . Since you were wondering.</p>
]]></description><pubDate>Fri, 06 Nov 2026 11:51:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=50391246</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50391246</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50391246</guid></item><item><title><![CDATA[New comment by internet_points in "From Linux to Wikipedia: How Volunteers Build the Internet"]]></title><description><![CDATA[
<p>> There is no cabal of evil tech that pushes this, but the results are the same.<p>I used to think this, I would repeat that old quote "It's not a conspiracy, the truth is more frightening, nobody is in control"<p>Then comes stuff like<p><a href="https://en.wikipedia.org/wiki/Halloween_documents#:~:text=that%20%22-,FUD" rel="nofollow">https://en.wikipedia.org/wiki/Halloween_documents#:~:text=th...</a><p>and<p><a href="https://www.economist.com/1843/2016/10/20/the-scientists-who-make-apps-addictive" rel="nofollow">https://www.economist.com/1843/2016/10/20/the-scientists-who...</a><p>and<p><a href="https://futurism.com/artificial-intelligence/microsoft-plots-addicted-to-its-ai" rel="nofollow">https://futurism.com/artificial-intelligence/microsoft-plots...</a><p>and<p><a href="https://cybernews.com/cybercrime/meta-fortune-fraudulent-ads-internal-documents-show/" rel="nofollow">https://cybernews.com/cybercrime/meta-fortune-fraudulent-ads...</a><p>and<p><a href="https://duckduckgo.com/?q=+inauguration+zuckerburg+musk+trump&iar=images&t=ffab" rel="nofollow">https://duckduckgo.com/?q=+inauguration+zuckerburg+musk+trum...</a><p>and<p><a href="https://ca.news.yahoo.com/dem-orders-congressional-probe-epstein-170246241.html" rel="nofollow">https://ca.news.yahoo.com/dem-orders-congressional-probe-eps...</a><p>and I'm left thinking well, if none of that covers the definition of evil cabal, then what does? How far can we move these goal posts?</p>
]]></description><pubDate>Fri, 06 Nov 2026 08:55:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=50389837</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50389837</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50389837</guid></item><item><title><![CDATA[New comment by internet_points in "I struggle to believe that AI R&D is ingenious"]]></title><description><![CDATA[
<p>and I'm guessing it was with "tool calling" ie. they can write a bunch of Lean proofs and hit compile and basically brute-force a whole bunch of hypotheses quickly?<p>Ie. the LLM itself isn't as "smart" as the combination of LLM, Lean, looping, search and vast gpu/cpu-time.</p>
]]></description><pubDate>Fri, 06 Nov 2026 08:38:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=50389701</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50389701</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50389701</guid></item><item><title><![CDATA[New comment by internet_points in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>Were you looking at another comment? I had to reread what I wrote, and I can't understand where you'd get the impression that I use it that much. I don't even use it daily (looking at my stats, it seems I used it less than every other day).<p>gpt5.4 pricing per million tokens is 
Input: $2.50
Cached input: $0.25
Output: $15.00<p>I tried re-running a rather long code review request I had lying around, and gptel says it spent 2.2k tokens; I don't know if that's input or output or what, but if we say it's output since that's the most expensive, then that single review cost me just $0.033.</p>
]]></description><pubDate>Thu, 05 Nov 2026 10:48:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=50377633</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50377633</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50377633</guid></item><item><title><![CDATA[New comment by internet_points in "Ask HN: What's your current AI agentic setup?"]]></title><description><![CDATA[
<p>1) What AI subscriptions are you personally paying for? (Claude, ChatGPT/Codex, Cursor, etc)<p>None.<p>2) Are you using models outside (or instead) of those subscriptions? For example, pay-as-you-go APIs, OpenRouter, or locally hosted models.<p>I have a few ChatGPT API credits. I think I've payed at most $40 in one year, using 5.4.<p>3) What coding harnesses and interfaces are you using? Are you sticking with the default CLIs or IDE integrations, or using alternatives like OpenCode, Pi, Aider, Muse Code, or custom-built harnesses?<p>Just gptel in a firejailed Emacs. I don't do tool calling. Mostly just code review (have personal scripts set up to get diffs and automatically redact stuff).<p>4) Are you using any agent orchestration or swarm tools?<p>No.<p>5) Are you using broader agent platforms like OpenClaw / Hermes Agent / Grok bot / Dots / Muse?<p>No.<p>I'd like to try agent stuff using a local model, but it seems quite expensive to set up. I don't feel comfortable giving so much access to OpenAI/Anthropic.</p>
]]></description><pubDate>Thu, 05 Nov 2026 09:58:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=50377307</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50377307</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50377307</guid></item><item><title><![CDATA[New comment by internet_points in "Resisting Cognitive Surrender"]]></title><description><![CDATA[
<p>The better an automatic control is, the fewer mistakes it makes, the fewer times the human needs to react, the more lax and less vigilant the human becomes -- and less skilled when they need to step in. Source: <a href="https://imgur.com/a/Vj2TaDz" rel="nofollow">https://imgur.com/a/Vj2TaDz</a></p>
]]></description><pubDate>Tue, 03 Nov 2026 08:48:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=50349593</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50349593</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50349593</guid></item><item><title><![CDATA[New comment by internet_points in "Show HN: I built a little browser game to practice Vim commands"]]></title><description><![CDATA[
<p>The best game to learn hjkl movement will always be nethack :)</p>
]]></description><pubDate>Tue, 03 Nov 2026 08:31:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=50349495</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50349495</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50349495</guid></item><item><title><![CDATA[New comment by internet_points in "Show HN: Subvocal – Talk to your computer without making noise"]]></title><description><![CDATA[
<p>Haha, I can't tell if this is a parody or not</p>
]]></description><pubDate>Mon, 02 Nov 2026 18:29:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=50341303</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50341303</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50341303</guid></item><item><title><![CDATA[Org-Mode November 2026: Fabulously Fancy [LaTeX] Fragments]]></title><description><![CDATA[
<p>Article URL: <a href="https://blog.tecosaur.net/tmio/2026-11-01-preview.html">https://blog.tecosaur.net/tmio/2026-11-01-preview.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=50334588">https://news.ycombinator.com/item?id=50334588</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 02 Nov 2026 09:10:46 +0000</pubDate><link>https://blog.tecosaur.net/tmio/2026-11-01-preview.html</link><dc:creator>internet_points</dc:creator><comments>https://news.ycombinator.com/item?id=50334588</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=50334588</guid></item></channel></rss>