<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: prymitive</title><link>https://news.ycombinator.com/user?id=prymitive</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Sun, 21 Jun 2026 03:34:12 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=prymitive" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by prymitive in "Temporary Cloudflare accounts for AI agents"]]></title><description><![CDATA[
<p>Maybe your agent could have a little blog where it keeps a diary of cool pages it read for you? And then you subscribe to that?</p>
]]></description><pubDate>Sat, 20 Jun 2026 19:30:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=48612212</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48612212</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48612212</guid></item><item><title><![CDATA[New comment by prymitive in "Companies rein in AI usage as costs strain budgets"]]></title><description><![CDATA[
<p>Partially because they think that once employees put enough context and rules into markdown files they can be fired and replaced by an online subscription.</p>
]]></description><pubDate>Fri, 19 Jun 2026 21:40:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=48603579</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48603579</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48603579</guid></item><item><title><![CDATA[New comment by prymitive in "Companies rein in AI usage as costs strain budgets"]]></title><description><![CDATA[
<p>IMHO it’s just good old fomo. They fear that the landscape will shift overnight and they’ll be left with a ton of useless meat bags instead of a pay as you go models that you can upgrade instantly every quarter.</p>
]]></description><pubDate>Fri, 19 Jun 2026 21:29:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=48603454</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48603454</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48603454</guid></item><item><title><![CDATA[New comment by prymitive in "Apple WWDC 2026"]]></title><description><![CDATA[
<p>The only thing that interested in is: did they fix screen brightness getting super dim even when the slider is at max? That’s incredibly annoying and frustrating, and it’s been like that since first 26 release.
And it’s a clear bug because brightness resets to expected level if I go to photos and open an HDR image.
I can wait for autocomplete that doesn’t suggest garbage 50% of the time, but this one is just too annoying.<p><a href="https://discussions.apple.com/thread/256141236" rel="nofollow">https://discussions.apple.com/thread/256141236</a></p>
]]></description><pubDate>Mon, 08 Jun 2026 18:43:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=48449591</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48449591</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48449591</guid></item><item><title><![CDATA[New comment by prymitive in "Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering"]]></title><description><![CDATA[
<p>AIshittification</p>
]]></description><pubDate>Sun, 07 Jun 2026 07:33:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=48432716</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48432716</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48432716</guid></item><item><title><![CDATA[New comment by prymitive in "Police in England and Wales told to halt AI use in court statements"]]></title><description><![CDATA[
<p>One can ask, what is a practical difference between “Check everything that it produces” and “Do all the work yourself”?<p>It’s not typing that’s the bottleneck, at least not often, so this is essentially assuming that you can do all the needed work without actually doing it, which is obviously wishful thinking.</p>
]]></description><pubDate>Sat, 06 Jun 2026 17:20:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=48426994</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48426994</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48426994</guid></item><item><title><![CDATA[New comment by prymitive in "Google will pay SpaceX $920M per month for compute"]]></title><description><![CDATA[
<p>All companies are now AI companies.
Just like a while ago all companies were suddenly Ads companies.
The entire tech sector is one big FOMO - once you reach certain scale you do exactly the same thing as everyone else.</p>
]]></description><pubDate>Sat, 06 Jun 2026 12:52:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=48424607</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48424607</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48424607</guid></item><item><title><![CDATA[New comment by prymitive in "Uber caps employee AI spending after blowing through budget in four months"]]></title><description><![CDATA[
<p>I have no idea how much I’ve spent, it’s invisible to me, the company doesn’t share it with me.
I have no idea what “1 credit” means in terms of $$$, is that 1$? 0.1? 0.01? Is it even a fixed price?
I have no idea how much will given take cost. Well, I can ask for a plan and extrapolate from that, but all perfectly reasonable looking plans eventually end up in a rabbit hole.
Providers keep introducing new models and each is more expensive while offering modest improvements, it’s a silent inflation.<p>So I personally can easily believe that. Especially that a lot of people will just try to see if model can make that huge improvement / refactoring they’ve been hoping to do a reality, or tons of experiments to validate ideas.</p>
]]></description><pubDate>Tue, 02 Jun 2026 21:22:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=48376490</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48376490</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48376490</guid></item><item><title><![CDATA[New comment by prymitive in "Google broke syncing for Fitbit scales"]]></title><description><![CDATA[
<p>I have an ancient Withings scale and a Fitbit, it used to be that Withings sends data straight to Fitbit but these days seems gone, so now I have Withings app writing to Apple Health and then Google Health reads from it. Great time to be alive</p>
]]></description><pubDate>Wed, 27 May 2026 07:57:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=48291088</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48291088</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48291088</guid></item><item><title><![CDATA[New comment by prymitive in "Dumb ways for an open source project to die"]]></title><description><![CDATA[
<p>Call me old but there was a time when “open source project” meant “I had a problem, this is my solution, if someone has the same problem then you are free to use my solution”.
These days is more:
- building personal brand
- showcasing your skills
- trying to outsmart somebody else, often because they didn’t merge your pr
- sometimes just having fun<p>And if you work for big org it’s also often “this looks vaguely similar to one of our epics so let’s start using it and demand 24/7 support”</p>
]]></description><pubDate>Tue, 19 May 2026 21:33:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=48199980</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48199980</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48199980</guid></item><item><title><![CDATA[New comment by prymitive in "Grafana Labs internal source code accessed"]]></title><description><![CDATA[
<p>One of the scalars in our feature matrix allowed for an attack vector to move beyond our security barrier causing an incident overflow</p>
]]></description><pubDate>Sun, 17 May 2026 11:35:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=48167972</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48167972</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48167972</guid></item><item><title><![CDATA[New comment by prymitive in "Bun Rust rewrite: "codebase fails basic miri checks, allows for UB in safe rust""]]></title><description><![CDATA[
<p>Any prediction market bets on what will they rewrite it into next week? Era of just-in-vibe software is here.</p>
]]></description><pubDate>Fri, 15 May 2026 19:27:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=48152775</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48152775</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48152775</guid></item><item><title><![CDATA[New comment by prymitive in "How Claude Code works in large codebases"]]></title><description><![CDATA[
<p>What I’m curious about is how well LLMs do when they create something from scratch, because so far my experience was with letting it fix issues or add features to existing codebase where I already shaped the general architecture and put in a lot of guardrails. But what if the architecture is unclear and there is nothing letting agent know if change breaks something or not?
My only experience with tiny codebase where it did a lot of scaffolding was poor - it did what I asked for, not what I needed. If i did more of the thinking myself I would realise it’s a code that works but doesn’t solve the problem I’m after.</p>
]]></description><pubDate>Fri, 15 May 2026 07:23:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=48145564</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48145564</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48145564</guid></item><item><title><![CDATA[New comment by prymitive in "Cloudflare to cut about 20% of its workforce"]]></title><description><![CDATA[
<p>It’s not like this is a factory floor where you process something coming in and AI suddenly makes the process more efficient and people are idle.
Every team in tech world has infinite backlog, you don’t fire 20% the minute someone manages to close a few tickets.</p>
]]></description><pubDate>Thu, 07 May 2026 20:55:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=48054837</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48054837</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48054837</guid></item><item><title><![CDATA[New comment by prymitive in "Cloudflare to cut about 20% of its workforce"]]></title><description><![CDATA[
<p>Obviously AI is just a  excuse</p>
]]></description><pubDate>Thu, 07 May 2026 20:48:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=48054756</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=48054756</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48054756</guid></item><item><title><![CDATA[New comment by prymitive in "Mercedes-Benz commits to bringing back physical buttons"]]></title><description><![CDATA[
<p>No alphabro wants to learn from anyone else, they already know everything</p>
]]></description><pubDate>Sun, 03 May 2026 15:58:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=47998252</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=47998252</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47998252</guid></item><item><title><![CDATA[New comment by prymitive in "Windows quality update: Progress we've made since March"]]></title><description><![CDATA[
<p>> You want to see what we’re doing, understand our decisions, and see progress through shipping. Second, a shared sense of pride.<p>So basically:
- recent changes are all crap
- so why did you make them?</p>
]]></description><pubDate>Sun, 03 May 2026 06:44:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=47994072</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=47994072</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47994072</guid></item><item><title><![CDATA[New comment by prymitive in "HERMES.md in commit messages causes requests to route to extra usage billing"]]></title><description><![CDATA[
<p>Sounds like somebody needs good numbers for IPO</p>
]]></description><pubDate>Wed, 29 Apr 2026 19:20:08 +0000</pubDate><link>https://news.ycombinator.com/item?id=47953076</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=47953076</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47953076</guid></item><item><title><![CDATA[New comment by prymitive in "Anker made its own chip to bring AI to all its products"]]></title><description><![CDATA[
<p>They own Eufy which sells cameras with main feature being “no subscription needed”, that are very unreliable and full of ads (which isn’t being advertised as much as lack of subscription). They do also go big on labelling a lot of simple features as AI where in reality it’s something as simple as “detect a person in a photo”.
I have Eufy cameras and it’s complete garbage, sadly competition is also mostly garbage.
Bold unsustainable claims at st the core of their business, it’s not just thumbnails.</p>
]]></description><pubDate>Wed, 22 Apr 2026 19:46:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=47868348</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=47868348</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47868348</guid></item><item><title><![CDATA[New comment by prymitive in "Less human AI agents, please"]]></title><description><![CDATA[
<p>That’s my daily experience too. There are a few more behaviours that really annoys me, like:
- it breaks my code, tests start to fail and it instantly says “these are all pre existing failures” and moves on like nothing happened
- or it wants to run some a command, I click the “nope” button and it just outputs “the user didn’t approve my command, I need to try again” and I need to click “nope” 10 more times or yell at it to stop
- and the absolute best is when instead of just editing 20 lines one after another it decides to use a script to save 3 nanoseconds, and it always results in some hot mess of botched edits that it then wants to revert by running git reset —hard and starting from zero. I’ve learned that it usually saves me time if I never let it run scripts.</p>
]]></description><pubDate>Tue, 21 Apr 2026 08:07:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=47845946</link><dc:creator>prymitive</dc:creator><comments>https://news.ycombinator.com/item?id=47845946</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47845946</guid></item></channel></rss>