<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: kaycey2022</title><link>https://news.ycombinator.com/user?id=kaycey2022</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 08 Jun 2026 17:09:01 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=kaycey2022" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by kaycey2022 in "Ask HN: What is your (AI) dev tech stack / workflow?"]]></title><description><![CDATA[
<p>I just ask whatever model I'm using, mostly GPT these days, to do the thing. First I discuss a plan of action and then go back and forth with it to settle on one. This is usually a long process and for complex features may even take a day or two. And then once I am satisfied, I ask it to implement. I skim over the code, it often generates too much code for my liking. I sometimes ask it to change things that I dont like. This is almost always to do with bad tests or not using existing code paths. I just work on one thing at a time.</p>
]]></description><pubDate>Sat, 06 Jun 2026 04:17:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=48421333</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=48421333</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48421333</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap)"]]></title><description><![CDATA[
<p>I dislike it because it feels like I’m doing someone else’s work for them, reviewing what they should have reviewed in the first place.</p>
]]></description><pubDate>Thu, 28 May 2026 01:44:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=48303309</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=48303309</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48303309</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Green card seekers must leave U.S. to apply, Trump administration says"]]></title><description><![CDATA[
<p>We carry the seeds of our own destruction they say. So this is a good thing. America should take care of their own citizens first. It is a good thing. Also there is a school of thought that says prosperity of any country is primarily a function of the kind of citizens they have, and how the country is able to leverage the intellect of its citizens. An important thesis of recent discussions of American prosperity is that a lot of it has been built up by the immigration of enterprising people into the US. So it can be argued that American prosperity is at the cost of prosperity of the rest of the world. And most of these things have compounding effects. The more intellect gathers in the US, that country can leap frog into the future at a far more vigorous pace than other could if most of these people were left inside their own countries. But in any case, these current events give us an opportunity into testing the thesis of American prosperity. Either balance will be brought to how global prosperity is distributed, or finally a country will be able to take care of its own citizens first. Either way this is all a great thing.</p>
]]></description><pubDate>Sun, 24 May 2026 12:47:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=48256854</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=48256854</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48256854</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Pausing New Challenges – Codecrafters"]]></title><description><![CDATA[
<p>Last 6 months vibecoding, I feel I have learned very little. You learn things like a high level executive or a manager. I can describe things at a very high level, but remain clueless how things work at the implementation level. It is just whatever code quality, architecture, common sense I learned earlier is carrying me through. Platforms like Codecrafters will be badly missed.</p>
]]></description><pubDate>Sat, 23 May 2026 14:24:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=48248001</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=48248001</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48248001</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Twin brothers wipe 96 government databases minutes after being fired"]]></title><description><![CDATA[
<p>Those are not red flags. Those are the actual thing. I think red flag is a heuristic that warns you about a course of action.</p>
]]></description><pubDate>Thu, 14 May 2026 16:40:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=48137801</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=48137801</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48137801</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Linux gaming is faster because Windows APIs are becoming Linux kernel features"]]></title><description><![CDATA[
<p>I was in the same boat. You should try running an AI agent to solve your problems. Works like a charm. Most of the times. The times it doesn't, it wasn't worth it anyway.</p>
]]></description><pubDate>Thu, 14 May 2026 14:15:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=48135753</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=48135753</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48135753</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Learning Software Architecture"]]></title><description><![CDATA[
<p>We can't even say something in public these days. All your comment needs is the trigger words or constructions<p>- That's why X works.
- Not X but Y.<p>And some moron will be in the replies, saying "LLM comment". I hate this world. But probably yeah. llm comment.</p>
]]></description><pubDate>Tue, 12 May 2026 12:05:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=48107091</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=48107091</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48107091</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Claude.ai and API unavailable [fixed]"]]></title><description><![CDATA[
<p>Arent they just on the hook for trillion dollars</p>
]]></description><pubDate>Thu, 30 Apr 2026 01:40:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=47957071</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=47957071</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47957071</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Muse Spark: Scaling towards personal superintelligence"]]></title><description><![CDATA[
<p>you can do way more than just coding with the coding agents.</p>
]]></description><pubDate>Thu, 09 Apr 2026 01:56:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=47698483</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=47698483</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47698483</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Claude Code users hitting usage limits 'way faster than expected'"]]></title><description><![CDATA[
<p>No. It's still shit. It can do some well contained tasks, but it is very less usable on production codebases than gpt or claude models. Mainly because of the usage limits and the lack of good environments for us to use it on. Anthropic gets away with this because claude code, as bad as it is, is still quite functional. Gemini cli and antigravity are utter trash in comparison.</p>
]]></description><pubDate>Tue, 31 Mar 2026 15:20:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=47588657</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=47588657</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47588657</guid></item><item><title><![CDATA[New comment by kaycey2022 in "An industrial piping contractor on Claude Code [video]"]]></title><description><![CDATA[
<p>scaling these solutions will prove to be counter productive. If you are thinking of scaling you are still trapped in the current paradigm. This plumber guy is only unique in that he read the news and pushed a little harder to see what the actual f is going on. In the days that come, every single person who is serious about their job will do and experience the same thing.<p>I'm not saying this particular individual is wrong in trying to build his solution to the market. Maybe there is some VC money to be made in this moment. But as AI in the workplace gets normalised, most people will either come up with solutions for their problems, or they will ask someone they know to help them with this.<p>scale will only matter if you are explicitly building a platform. That will still require real software engineering skills.<p>As for hardware interfacing, if I am not mistaken, almost all companies selling hardware right now still behave like babies when it comes to users getting access to the software inside it. They void warrantees, sue them, so on etc. For ambitious user driven software innovations in the hardware space the companies should open up their interfaces. I don't see this happening at all not only because of the companies' greed but also for regulatory and safety reasons.</p>
]]></description><pubDate>Sat, 21 Mar 2026 16:21:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=47468411</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=47468411</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47468411</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Book: The Emerging Science of Machine Learning Benchmarks"]]></title><description><![CDATA[
<p>sry just a joke man</p>
]]></description><pubDate>Fri, 20 Mar 2026 10:40:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=47452792</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=47452792</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47452792</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Anthropic takes legal action against OpenCode"]]></title><description><![CDATA[
<p>there is nothing about claude code that prevents you from using it for non coding use cases. nothing that happens in open code or any harness for that matter is hidden from anthropic. neither does open code allow access in some nefarious use case that claude code does not.<p>the difference is not like the difference between gmail and gmailfs like you seem to be misunderstanding. a more accurate comparison would be the difference between curl, or httpie vs postman.</p>
]]></description><pubDate>Fri, 20 Mar 2026 04:12:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=47450406</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=47450406</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47450406</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Anthropic takes legal action against OpenCode"]]></title><description><![CDATA[
<p>I don't think it's any of that. It's plain as day to see that as the owners of the API they can see every request, collect every metric they need. The routing can easily be done in the API gateway layer and doesn't depend on the harness at all. Good harnesses are not performing acrobatics around user behaviour to improve anything. They just understand the provider API very well and translate tool calls really well. Then they get out of the way to let the magic happen.<p>This is about controlling user behaviour, resisting standardisation efforts, to keep subscribers hooked to their models. If they keep their users on claude code, they don't have to adapt to evolving harness standards when shown increased usage across different harnesses. They will try to keep everything on their terms, on their poor quality of engineering, and the users accustomed to claude behaviour will be left with no quick way to switch to other models.<p>This strategy will keep working as long as they own a top tier frontier model with enough marketing hype behind it to blind unsophisticated users.</p>
]]></description><pubDate>Fri, 20 Mar 2026 04:04:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=47450346</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=47450346</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47450346</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Anthropic takes legal action against OpenCode"]]></title><description><![CDATA[
<p>This is clearest reason for us to accustom ourselves to using open weight models on open source harnesses. Whatever advantages the frontier closed models offer, this will turn into ash in the mouth, when the enshittification cycle begins. And don't be mistaken, it will begin. There is no precedent which can claim otherwise.<p>I am sure the models themselves are being RLHF tuned to work very well with the proprietary agent harnesses. This is all turning into a huge trap right in front of our eyes and the target is not just programmers but also companies whose core product involves software production.</p>
]]></description><pubDate>Fri, 20 Mar 2026 03:43:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=47450231</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=47450231</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47450231</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Book: The Emerging Science of Machine Learning Benchmarks"]]></title><description><![CDATA[
<p>You honestly don't know of Moritz Hardt?</p>
]]></description><pubDate>Thu, 19 Mar 2026 04:46:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=47435062</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=47435062</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47435062</guid></item><item><title><![CDATA[New comment by kaycey2022 in "Agentic Engineering Patterns"]]></title><description><![CDATA[
<p>Agile Intelligence</p>
]]></description><pubDate>Wed, 04 Mar 2026 15:37:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=47249047</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=47249047</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47249047</guid></item><item><title><![CDATA[New comment by kaycey2022 in "“Microslop” filtered in the official Microsoft Copilot Discord server"]]></title><description><![CDATA[
<p>The step after that is to sync copilot screenshots with webcam footage of the user to build a marketing database matching user’s emotional responses to on screen content.</p>
]]></description><pubDate>Tue, 03 Mar 2026 03:35:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=47227680</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=47227680</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47227680</guid></item><item><title><![CDATA[New comment by kaycey2022 in "If AI writes code, should the session be part of the commit?"]]></title><description><![CDATA[
<p>This feels woefully inadequate. It should be saving everything. Not just the prompts and replies, but also the tool calls and skill invocations. If that is too much, then why even save anything in the session?<p>Right now this paradigm is so novel to us that we don’t know if what is being saved is useful in anyway or just hoarding garbage.<p>There are some who (rightly IMO) just neatly squash their commits and destroy the working branch after merging. There are others who would rather preserve everything.</p>
]]></description><pubDate>Mon, 02 Mar 2026 10:42:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=47216202</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=47216202</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47216202</guid></item><item><title><![CDATA[New comment by kaycey2022 in "This system can go fuck itself and burn in hell"]]></title><description><![CDATA[
<p>This was rough to read. No wonder a growing number of people in your country hate immigrants so much.<p>Although, rationally speaking they are not be the cause of so much misfortune. People should do whatever they can to get ahead. No one should accept poverty. As long as you don’t cut the throat of other innocents, it’s all fine.<p>One thing I would say is don’t put yourself down - like good things aren’t for you. I wouldn’t frame it as you don’t deserve. Everyone deserves a good life. Deserve takes you down a self destructive path. But because of the circumstance if your birth, you can’t have it - now.</p>
]]></description><pubDate>Mon, 02 Mar 2026 04:46:47 +0000</pubDate><link>https://news.ycombinator.com/item?id=47213994</link><dc:creator>kaycey2022</dc:creator><comments>https://news.ycombinator.com/item?id=47213994</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47213994</guid></item></channel></rss>