<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: parentheses</title><link>https://news.ycombinator.com/user?id=parentheses</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sat, 20 Jun 2026 08:14:44 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=parentheses" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by parentheses in "Ask HN: What are you working on? (June 2026)"]]></title><description><![CDATA[
<p>You're right in my neighborhood. Signed up! Fantastic!</p>
]]></description><pubDate>Mon, 15 Jun 2026 06:24:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=48537338</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=48537338</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48537338</guid></item><item><title><![CDATA[New comment by parentheses in "I manage teams without a single call"]]></title><description><![CDATA[
<p>Building a team to operate based on your own personal preferences is selfish leadership... or even dictatorship.<p>There's a very strong "focus culture" which relies on the idea that work is not done in meetings. This is wrong. Progress comes in many forms.</p>
]]></description><pubDate>Mon, 25 May 2026 16:45:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=48268887</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=48268887</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48268887</guid></item><item><title><![CDATA[Ask HN: Reading AI Assisted Essays]]></title><description><![CDATA[
<p>Something I've been pondering for a while now is how I feel about AI produced content.<p>I find a lot of essays that are clearly AI assisted but I am able to get a feeling that the person who produced it put time and effort into writing it. My current model is something like:<p>If it feels like AI generated content where I feel a certain minimum amount of effort was made to shape the content, I don't mind reading it.<p>Take, for example, my own. I am quite self conscious about sounding very robotic and using a lot of the same turns of phrase. So I write an article in my voice, then have the droids zhuzh it up for me. Make the text a bit more interesting. Add some sarcasm where I struggled with articulating it. Make the pacing and rhythm nicer. Shorten my often verbose way of saying things.<p>I feel I try pretty hard to make it my own because I don't like the idea of stamping my brand on something I didn't put some proper effort into.<p>I would love to hear how you all feel and what you think of this as authors and readers.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48170026">https://news.ycombinator.com/item?id=48170026</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 17 May 2026 15:54:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=48170026</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=48170026</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48170026</guid></item><item><title><![CDATA[New comment by parentheses in "Write some software, give it away for free"]]></title><description><![CDATA[
<p>With AI it feels writing software that is open is less attractive. It's hard to trust OSS made recently b/c you can tell if someone knows what they're doing and even spent any time on quality. Also, often times people don't reach for software others make (unless it's boring and old stuff, in which case this advice doesn't apply.)</p>
]]></description><pubDate>Tue, 05 May 2026 23:53:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=48030378</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=48030378</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48030378</guid></item><item><title><![CDATA[New comment by parentheses in "A couple million lines of Haskell: Production engineering at Mercury"]]></title><description><![CDATA[
<p>IMO types are the main lever you can use other than procedural abstraction. I feel that Haskell gives you both in a way that marries them for maximum constraint-building. Constraints that prevent illogical or illegal programs are the bread and butter of reliable software.</p>
]]></description><pubDate>Sun, 03 May 2026 18:38:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=47999991</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47999991</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47999991</guid></item><item><title><![CDATA[New comment by parentheses in "Show HN: Apple's Sharp Running in the Browser via ONNX Runtime Web"]]></title><description><![CDATA[
<p>I've been poking at running LLMs in the browser. It feels like we're definitely close (<1 year) to seeing real use cases there.<p>Ubiquity and coverage of devices is what will take longest. Largely dependent on how well we can shrink models with similar performance and how much we can accelerate mobile devices. This feels like it's but further (<3 years?)</p>
]]></description><pubDate>Sun, 03 May 2026 18:25:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=47999850</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47999850</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47999850</guid></item><item><title><![CDATA[New comment by parentheses in "LLMs consistently pick resumes they generate over ones by humans or other models"]]></title><description><![CDATA[
<p>Reading only the abstract: LLMs prefer output of their own generation over humans or even other models.<p>This is a very good reason to avoid using model-generated data to train future models. We'd be deepening this bias by continuing to do that, essentially forcing society to reshape their output using LLMs to increase engagement. This feels like a form of enshittification that doesn't just touch one product but all of society.</p>
]]></description><pubDate>Sat, 02 May 2026 16:30:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=47987818</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47987818</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47987818</guid></item><item><title><![CDATA[New comment by parentheses in "Opus 4.7 knows the real Kelsey"]]></title><description><![CDATA[
<p>I have been pondering this for a while. Cat's out of the bag.<p>Maybe the better way to author your work is to:<p>1. Write what you want<p>2. Loop through a random set of "tumbler" skills that preserve meaning<p>3. Finally pass the output through a "my style" skill that applies what you about<p>In order for this to work the "my style" would have to be a very common-place style.</p>
]]></description><pubDate>Fri, 01 May 2026 06:12:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=47971730</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47971730</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47971730</guid></item><item><title><![CDATA[New comment by parentheses in "Cursor Camp"]]></title><description><![CDATA[
<p>Legit first post I've wanted to upvote in a long time.</p>
]]></description><pubDate>Wed, 29 Apr 2026 22:10:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=47955398</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47955398</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47955398</guid></item><item><title><![CDATA[New comment by parentheses in "We need a federation of forges"]]></title><description><![CDATA[
<p>This type of thing requires an economic driver to monetize the service.<p>I'd have a strong inclination to run such software if I knew that I was both helping host repos and getting paid.</p>
]]></description><pubDate>Wed, 29 Apr 2026 22:07:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=47955374</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47955374</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47955374</guid></item><item><title><![CDATA[New comment by parentheses in "HERMES.md in commit messages causes requests to route to extra usage billing"]]></title><description><![CDATA[
<p>I feel like it's not news that a company with (probably) millions of DAU is not able to handle a single case like this one.<p>At the same time, it's clear that after this happened, Anthropic took action. 3 DAYS AGO! (<a href="https://news.ycombinator.com/item?id=47954655">https://news.ycombinator.com/item?id=47954655</a>)<p>That's before this comment was made on the issue:<p><a href="https://github.com/anthropics/claude-code/issues/53262#issuecomment-4322927242" rel="nofollow">https://github.com/anthropics/claude-code/issues/53262#issue...</a><p>I'm surprised Anthropic didn't also say this on the issue. Weird that they wouldn't. It seems to have made for unnecessary bad PR.<p>It feels to me that Anthropic is less focused on quality, and more focused on PR stunts/flash. My experience with Claude is always "it's pretty and feels cool", where-as codex feels like "solid and boring". I realize I'm probably biased. Am I alone in this thinking?</p>
]]></description><pubDate>Wed, 29 Apr 2026 21:48:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=47955192</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47955192</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47955192</guid></item><item><title><![CDATA[New comment by parentheses in "SWE-bench Verified no longer measures frontier coding capabilities"]]></title><description><![CDATA[
<p>The timing makes me wonder if this is a direct response to Deepseek V4 having performance comparable to SOTA models.</p>
]]></description><pubDate>Sun, 26 Apr 2026 17:34:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=47912111</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47912111</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47912111</guid></item><item><title><![CDATA[New comment by parentheses in "How I Use Unspent Tokens"]]></title><description><![CDATA[
<p>I built a small tool that makes one cleanup commit at a time, keeps it only if tests pass, and moves on. The article is about how it grew from that basic loop into taste files, staged migrations, and a way to keep repos getting a little cleaner in the background.<p><a href="https://github.com/bigH/continuous-refactoring" rel="nofollow">https://github.com/bigH/continuous-refactoring</a></p>
]]></description><pubDate>Wed, 22 Apr 2026 20:34:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=47868960</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47868960</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47868960</guid></item><item><title><![CDATA[How I Use Unspent Tokens]]></title><description><![CDATA[
<p>Article URL: <a href="https://artisincode.com/essays/how-i-use-unspent-tokens/">https://artisincode.com/essays/how-i-use-unspent-tokens/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47868955">https://news.ycombinator.com/item?id=47868955</a></p>
<p>Points: 24</p>
<p># Comments: 2</p>
]]></description><pubDate>Wed, 22 Apr 2026 20:34:00 +0000</pubDate><link>https://artisincode.com/essays/how-i-use-unspent-tokens/</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47868955</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47868955</guid></item><item><title><![CDATA[New comment by parentheses in "Live Translation, Running in the Browser"]]></title><description><![CDATA[
<p>Been tinkering on my personal site and wanted to add some AI features without being the one paying for tokens on every visit. So I went looking at how close browser-side inference actually is to practical. Closer than I expected.<p>The post is less a tutorial and more me walking through what it felt like. Kicking tires on random models, getting one to actually run, then doing the small unglamorous work to turn "demo" into something I'd put in front of a reader.<p>Related: <a href="https://news.ycombinator.com/item?id=47851111">https://news.ycombinator.com/item?id=47851111</a></p>
]]></description><pubDate>Tue, 21 Apr 2026 17:15:33 +0000</pubDate><link>https://news.ycombinator.com/item?id=47851648</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47851648</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47851648</guid></item><item><title><![CDATA[Live Translation, Running in the Browser]]></title><description><![CDATA[
<p>Article URL: <a href="https://artisincode.com/essays/live-translation-right-in-the-browser/">https://artisincode.com/essays/live-translation-right-in-the-browser/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47851640">https://news.ycombinator.com/item?id=47851640</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 21 Apr 2026 17:14:59 +0000</pubDate><link>https://artisincode.com/essays/live-translation-right-in-the-browser/</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47851640</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47851640</guid></item><item><title><![CDATA[New comment by parentheses in "TranslateGemma Running in the Browser"]]></title><description><![CDATA[
<p>I added live translation to this site, wrote about the weird edges, then made this little playground to mess with them directly. Proper nouns, tags and markdown syntax were always coming through weird, so this helped me investigate.<p>TranslateGemma was one of the few models I tried. Something interesting I noticed is that each model has a different expectation of interface (fields passed in, naming of those fields and such.)<p>HN Post of Article:<p><a href="https://news.ycombinator.com/item?id=47808030">https://news.ycombinator.com/item?id=47808030</a></p>
]]></description><pubDate>Tue, 21 Apr 2026 16:35:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=47851124</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47851124</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47851124</guid></item><item><title><![CDATA[TranslateGemma Running in the Browser]]></title><description><![CDATA[
<p>Article URL: <a href="https://artisincode.com/playground/translation/">https://artisincode.com/playground/translation/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47851111">https://news.ycombinator.com/item?id=47851111</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 21 Apr 2026 16:34:12 +0000</pubDate><link>https://artisincode.com/playground/translation/</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47851111</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47851111</guid></item><item><title><![CDATA[New comment by parentheses in "Live Translation, Right in the Browser"]]></title><description><![CDATA[
<p>Been tinkering on my personal site and wanted to add some AI features without being the one paying for tokens on every visit. So I went looking at how close browser-side inference actually is to practical. Closer than I expected.<p>The post is less a tutorial and more me walking through what it felt like. Kicking tires on random models, getting one to actually run, then doing the small unglamorous work to turn "demo" into something I'd put in front of a reader.</p>
]]></description><pubDate>Fri, 17 Apr 2026 18:30:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=47809049</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47809049</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47809049</guid></item><item><title><![CDATA[Live Translation, Right in the Browser]]></title><description><![CDATA[
<p>Article URL: <a href="https://artisincode.com/essays/live-translation-right-in-the-browser/">https://artisincode.com/essays/live-translation-right-in-the-browser/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47808030">https://news.ycombinator.com/item?id=47808030</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Fri, 17 Apr 2026 17:00:03 +0000</pubDate><link>https://artisincode.com/essays/live-translation-right-in-the-browser/</link><dc:creator>parentheses</dc:creator><comments>https://news.ycombinator.com/item?id=47808030</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47808030</guid></item></channel></rss>