Hacker Newsnew | past | comments | ask | show | jobs | submit | f311a's commentslogin

Why are so many people so obsessed with feeding as many prompts/data as possible to LLMs and generating millions of lines of code?

What are you gonna do with the results that are usually slop?


If the slop passes my tests, then I'm going to use it for precisely the role that motivated the creation of it in the first place. If the slop is functional then I don't care that it's slop.

I've replaced half my desktop environment with this manner of slop, custom made for my idiosyncratic tastes and preferences.


> Wine/Proton have made far more in-roads in being able to run Windows

Yeah, they can even run modern games, which ReactOS can't. It can't even run on modern hardware properly.

It's a nice project, though. Good progress for a hobby project, and it's still going after 30 years!


For ML/AI/Comp sci articles, providing reproducible code is a great option. Basically, PoC or GTFO.

The most annoying ones are those which discuss loosely the methodology but then fail to publish the weights or any real algorithms.

It's like buying a piece of furniture from IKEA, except you just get an Allen key, a hint at what parts to buy, and blurry instructions.


This is so egregious. The value of such papers is basically nothing but they're extremely common.

It worked well for me when people were stealing my articles, pretending they wrote them. One tweet or mention in Linkedin and the article is gone.

Plagiarism is much different than collaborating on open source projects but I'm glad that calling them out worked.

How would it work if LLMs provide incorrect reports in the first place? Have a look at the actual HackerOne reports and their comments.

The problem is the complete stupidity of people. They use LLMs to convince the author of the curl that he is not correct about saying that the report is hallucinated. Instead of generating ten LLM comments and doubling down on their incorrect report, they could use a bit of brain power to actually validate the report. It does not even require a lot of skills, you have to manually tests it.


Let the reporter duke it out with the project's gatekeeping LLM. If it keeps going on for long enough a human can quickly skim the exchange. It should be immediately obvious if the reporter is making sensible rebuttals or just throwing more slop at the wall.

I think fighting fire with fire is likely the correct answer here.


Imagine the amount of slop PRs if it was open source. They don’t want to taste their own medicine

Reading their GitHub issues already is like reading through the diary entries of spurned lovers. I can only imagine the PRs.

It’s not like you needed LLMs for quickjs which already had known and unpatched problems. It’s a toy project. It would be cool to see exploits for something like curl.

Just look at the code quality produced by these loops. That's all you need to know about it.

It's complete garbage, and since it runs in a loop, the amount of garbage multiplies over time.


I don’t think anyone serious would recommend it for serious production systems. I respect the Ralph technique as a fascinating learning exercise in understanding llm context windows and how to squeeze more performance (read: quality) from today’s models

Even if in the absolute the ceiling remains low, it’s interesting the degree to which good context engineering raises it


How is it a “fascinating learning exercise” when the intention is to run the model in a closed loop with zero transparency. Running a black box in a black box to learn? What signals are you even listening to to determine whether your context engineering is good or whether the quality has improved aside from a brief glimpse at the final product. So essentially every time I want to test a prompt I waste $100 on Claude and have it an entire project for me?

I’m all for AI and it’s evident that the future of AI is more transparency (MLOPs, tracing, mech interp, AI safety) not less.


Current transparency is rubbish but people will continue to put up with it if they're getting decent output quality

there is the theoretical "how the world should be" and there is the practical "what's working today" - decry the latter and wait around for the former at your peril

You probably wouldn't use it for anything serious, but I've Ralphed a couple of personal tools: Mac menu bar apps mostly. It works reasonably well so long as you do the prep upfront and prepare a decent spec and plan. No idea of the code quality because I wouldn't know good swift code from a hole in the head, but the apps work and scratch the itch that motivated them.

I do not understand where this Ralph hype is coming from. Back when Claude 4.0 came out and it began to become actually useful, I already tried something like this. Every time it was a complete and utter failure.

And this dream of "having Claude implement an entire project from start to finish without intervention" came crashing down with this realization: Coding assistants 100% need human guidance.


> The use of em-dashes, which on most keyboard require a special key-combination that most people don’t know

Most people probably don't know, but I think on HN at least half of the users know how to do it.

It sucks to do this on Windows, but at least on Mac it's super easy and the shortcut makes perfect sense.


I don't have strong negative feelings about the era of LLM writing, but I resent that it has taken the em-dash from me. I have long used them as a strong disjunctive pause, stronger than a semicolon. I have gone back to semicolons after many instances of my comments or writing being dismissed as AI.

I will still sometimes use a pair of them for an abrupt appositive that stands out more than commas, as this seems to trigger people's AI radar less?


One way to use em-dash and look human is to write it incorrectly with two hyphens: --

I still use 'em. Fuck what everybody else thinks.

There's always the 3-em dash⸻a dastardly long strike.

That is fantastic.

At this point I almost look forward to some idiot calling me AI because they don't like what I said. I should start keeping score.

I can’t be the only one who has ever read https://practicaltypography.com/hyphens-and-dashes.html

This would have been very helpful three years ago, before I permanently stopped using em-dashes to not have my writing confused with LLM's.

I suspect whatever you try to do to not appear to be an LLM… LLM's also will do in time.

Might as well be yourself.


Indeed. I found that recently, Claude has been using hyphens instead of emdashes.

I've been left wondering when is the world going to find out about Input Method Editor.

It lets users type all sorts of ‡s, (*´ڡ`●)s, 2026/01/19s, by name, on Windows, Mac, Linux, through pc101, standard dvorak, your custom qmk config, anywhere without much prior knowledge. All it takes is to have a little proto-AI that can range from floppy sizes to at most few hundred MBs in size, rewriting your input somewhere between the physical keyboard and text input API.

If I wanted em–dashes, I can do just that instantly – I'm on Windows and I don't know what are the key combinations. Doesn't matter. I say "emdash" and here be an em-dash. There should be the equivalent to this thing for everybody.


Now I'm actually curious to see statistics regarding the usage of em-dashes on HN before and after AI took over. The data is public, right? I'd do it myself, but unfortunately I'm lazy.

Someone did just that!

Show HN: Hacker News em dash user leaderboard pre-ChatGPT - https://news.ycombinator.com/item?id=45071722 - Aug 2025 (266 comments)

... which I'm proud to say originated here: https://news.ycombinator.com/item?id=45046883.


Ha ha, my first use of an em-dash on HN was 2016 which was the year I started my account.

I'm safe. It must be one of you that are the LLM!

(Hey, I'm #21 on the leaderboard!).


First time I’m hearing about a shortcut for this. I always use 2 hyphens. Is that not considered an em-dash ?

You are absolutely right — most internet users don't know the specific keyboard combination to make an em dash and substitute it with two hyphens. On some websites it is automatically converted into an em dash. If you would like to know more about this important punctuation symbol and it's significance in identitifying ai writing, please let me know.

Wow thanks for the enlightenment. I dug into this a bit and found out:

Hyphen (-) — the one on your keyboard. For compound words like “well-known.”

En dash (–) — medium length, for ranges like 2020–2024. Mac: Option + hyphen. Windows: Alt + 0150.

Em dash (—) — the long one, for breaks in thought. Mac: Option + Shift + hyphen. Windows: Alt + 0151.

And now I also understand why having plenty of actual em-dashes (not double hyphens) is an “AI tell”.


If you have the compose key enabled it's trivial to write all sorts of things. Em dash is compose (right alt for me) ---

En dash is compose --.

You can type other fun things like section symbol (compose So) and fractions like ⅐ with compose 17, degree symbol (compose oo) etc.

https://itsfoss.com/compose-key-gnome-linux/

On phones you merely long press hyphen to get the longer dash options.


Thanks for that. I had no idea either. I'm genuinely surprised Windows buries such a crucial thing like this. Or why they even bothered adding it in the first place when it's so complicated.

The Windows version is an escape hatch for keying in any arbitrary character code, hence why it's so convoluted. You need to know which code you're after.

To be fair, the alt-input is a generalized system for inputting Unicode characters outside the set keyboard layout. So it's not like they added this input specifically. Still, the em dash really should have an easier input method given how crucial a symbol it is.

It's a generalized system for entering code page glyphs that was extended to support Unicode. 0150 and 0151 only work if you are on CP1252 as those aren't the Unicode code points.

And Em Dash is trivially easy on iOS — you simply hold press on the regular dash button - I’ve been using it for years and am not stopping because people might suddenly accuse me of being an AI.

Thanks for delving into this key insight!

No it's not the same. Note there are medium and long as well.

That said I always use -- myself. I don't think about pressing some keyboard combo to emphasise a point.


The long --- if you're that way minded --- is just 3 hyphens :)

Yep I realize this now, as I said in my other comment.

Yeah, it's

- Servo's HTML parser

- Servo's CSS parser

- QuickJS for JS

- selectors for CSS selector matching

- resvg for SVG rendering

- egui, wgpu, and tiny-skia for rendering

- tungstenite for WebSocket support

And all of that has 3M of lines!


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: