Hacker News: localhoster

New comment by localhoster in "Scriptc by Vercel: TypeScript-to-Native compiler, no JavaScript engine in binary"

localhoster — Mon, 27 Jul 2026 05:10:18 +0000

Funny to see vercel is loosing all credibility under the influence of AI. Never liked their products anyway, so I believe it's a net positive for the industry :)

New comment by localhoster in "How we measured AI writing across arXiv, and where the measurement breaks"

localhoster — Tue, 21 Jul 2026 08:26:24 +0000

I once read a comment on hn that says that ai detection in writing is so hard because text doesn't hold enough information. Now I'm no researcher,but that intuitivly makes sense to me. I mean, apart from the obvious cases, how can you detect ai written text?

New comment by localhoster in "Searchable field-level encryption on Supabase with CipherStash"

localhoster — Sun, 19 Jul 2026 07:52:48 +0000

Looking at their website, reading through abit, and seeing the comments here. Guys, this website is entirely ai generated, which might indicate about their product some. Not saying that they are lieing or anything, but expect a wall of text that no one really read through, and expect to (pun intended) cipher out the details.

New comment by localhoster in "Does code cleanliness affect coding agents? A controlled minimal-pair study"

localhoster — Mon, 06 Jul 2026 06:07:53 +0000

If we don't write the codebase, we don't write the tests, and the agents are modifying it, what even considered a messy codebase? Too many files? Too little files? Related code spread accros many files? What is considered a messy codebase?

Have you even seen one ever?

Also, not checking if it breaks unrelated tests is wild, good software is written by modifying the "just right" amount of code to get your result.

If you break _unrelated_ tests than you most likely didn't changed the right amount of code.

Idk I call bs.

New comment by localhoster in "I do not feel like a programmer anymore"

localhoster — Wed, 01 Jul 2026 08:40:30 +0000

The tiem that took experienced programmers to hand over their entire development process to AI was so remarkably fast, that it got me to believe that there are almost no programmers that enjoyed solving problems.

Once, my teacher in school told me that a software engineer needs to have some sadasim in it, because it will need to enjoy the pain of being stuck on a problem. I no longer believe this is true.

Most people are in it for the money, the status, the comfortable conditions, or maybe because this is the blue collar of the 21st century.

The people who are in it for the love of the game, are very little.

New comment by localhoster in "Godot will no longer accept AI-authored code contributions"

localhoster — Wed, 01 Jul 2026 08:30:28 +0000

While I agree with the general message, and wish it will eventually radiate to cooperations as well, it is obviously a decision driven by feelings, not logic.

The idea that you can't trust code that was generated by heavy users of AI, because _they_ don't understand it enough to fix it, is false, because they can use AI to fix it.

In general, I have hard time understanding how one might even block other contributors from using ai.

New comment by localhoster in "Show HN: Bored People Chat – Anonymous global chat room"

localhoster — Tue, 30 Jun 2026 06:42:24 +0000

> LLM text in user interfaces is like tailwind css, linkedin broetry and hustle culture had a demented lovechild.

next level

New comment by localhoster in "The Typing Was the Safety Harness"

localhoster — Wed, 17 Jun 2026 14:33:02 +0000

I've felt this from the beginning. But I have yet found. A way to communicate this without sound like "that guy".

Truth is that when you give people a "do-for-me" button they are going to be clicking it like it owes them money, and that there is nothing you can say that will tame people down a bit. The truth is also that most developers are... Mediocre... They have hard time thinking, and have hard time having that hard time. So trying to convince them to go back is like saying to them "become mediocre again". And while with ai they are still mediocre, _they_ don't feel like one.

So here we are, and the only thing we can do is to wave and smile as our train is leaving the station.

New comment by localhoster in "Why I'm Forced to Say Farewell: Google Management Has Lost Its Moral Compass"

localhoster — Thu, 11 Jun 2026 22:42:41 +0000

Not that I care in particular

But claiming that google lost it's "moral compass" just now is a claim only rich people can make because they retire, not quit.

Google is literally the largest, most organized, tracking and profiling company in the world. Which they tend to grow even larger with the rise of LLMs.

Turning a blind eye of that for the opportunity or whatever, and than claim that _just now_ they lost their moral compass, is being a hypocrite.

New comment by localhoster in "Software is made between commits"

localhoster — Thu, 11 Jun 2026 17:25:09 +0000

Sad to see zed going the same route everybody is screaming them not to. Altough, I never expected otherwise.

New comment by localhoster in "FPS.cob: A first person shooter in COBOL"

localhoster — Thu, 11 Jun 2026 17:19:04 +0000

We need to start putting guardrails on hn to not allow those esoteric projects to be published. Before ai, it was impressive that a person has that much passion and dedication to go down the rabbit hole, and it usually comes back with some cool anacdotes that are nice to read.

Today, it's shallow, emptied out of the content.

It's not impressive that Claude wrote it, it was impressive if you have written it, OP.

New comment by localhoster in "Claude Fable 5"

localhoster — Tue, 09 Jun 2026 20:31:56 +0000

is it just me, or this model is simply not available in cc?

the opus 4.8 I assumed wasnt available to enterprise seats, but it explicitly says cc that fable is available in cc. I can't find it, and im on latest version.

AI in the Workplace – Part 2

localhoster — Tue, 09 Jun 2026 15:13:32 +0000

I'm convinced that majority of developers never liked development. They, perhaps, like the money, or the status, or other aspects in the work. But they most certainly don't like development. I have people in my workplace that, in the last 6 months, have been only interacting with other colleagues, through Claude. They responses go through Claude, their code, their answers on their PRs, their design docs. Everything.

THIS IS THE MAJORITY.

I have to lie about my usage, and run tokenmaxxers, just to not look like "that guy" - to put my self in the spotlight.

People say "just go with it" but I can't. I just can't. Even in my usage today, I'm in constant fear that i'm responsible about stuff I didn't make. Anything I haven't written by hand, I just can't claim to be mine. Decisions I haven't make, are not my decisions.

I get that AI unlocks "massive productivity gains" but I just don't experiencing it. Now, instead I have to work twice as hard when I interact with any product any of my collueages produce.

Comments URL: https://news.ycombinator.com/item?id=48462192

Points: 2

# Comments: 0

New comment by localhoster in "Ask HN: AI efficiency in the workplace"

localhoster — Fri, 05 Jun 2026 07:46:32 +0000

not in a position of doing that lul

New comment by localhoster in "VoidZero Is Joining Cloudflare"

localhoster — Thu, 04 Jun 2026 14:40:05 +0000

Will it be the next Bun?

Ask HN: AI efficiency in the workplace

localhoster — Thu, 04 Jun 2026 12:47:02 +0000

Someone at my workplace took 3 days to write a PROMPT to Claude to write a PRD. It generated magnificent 12 notion pages with graphs, schema defenitions, expected behaviors, what-have-you. I read through all of them and raised some questions regrading the architecture he decided to go with, as he went on a different direction that what we discussed, and thats OK. Most of his responses where "oh just ignore that, claude added that". What are we even doing here? The same 3 days could've been spent writing the PRD by hand. Sure, it might not have been so as polished looking as the former, but at least it was accurate! This is exactly my pain with LLMs, they make loads of text, where, they appear efficient. Where actual efficiency is having the least amount of text to describe the feature.

I truly don't know what to do in this area, this goes against the whole premise of writing things up.

Comments URL: https://news.ycombinator.com/item?id=48397889

Points: 4

# Comments: 5

New comment by localhoster in "Gooey: A GPU-accelerated UI framework for Zig"

localhoster — Thu, 04 Jun 2026 12:29:04 +0000

Yavos - yet another vibe coded shit

New comment by localhoster in "Show HN: Uruky (EU-based Kagi alternative) now has Image Search and URL Rewrites"

localhoster — Thu, 04 Jun 2026 12:24:47 +0000

Yavos - Yet Another Vibe-cOded Service :)

New comment by localhoster in "SQLite is all you need for durable workflows"

localhoster — Fri, 29 May 2026 19:01:10 +0000

Idk if this article was vibe written or the author just "got adjusted" but it's clearly is, and it's unreadable. Man this becomes anmoying

New comment by localhoster in "I bypassed AWS API Gateway auth with a trailing slash. Got $12K bounty"

localhoster — Tue, 26 May 2026 11:50:46 +0000

Tbh I always wondered how are we still matching routes using regex and not something like a radix tree? That would eliminate these kinds of issues no?