For the best experience on desktop, install the Chrome extension to track your reading on news.ycombinator.com
Hacker Newsnew | past | comments | ask | show | jobs | submit | history | croemer's commentsregister

And it turns out at least the part about Rust and locks is plain wrong. What a surprise: https://news.ycombinator.com/reply?id=47676938&goto=item%3Fi...

I had a look at the (vibe coded) repro linked in the article to see if it holds up: https://github.com/juxt/agc-lgyro-lock-leak-bug/blob/c378438...

The repro runs on my computer, that's positive.

However, Phase 5 (deadlock demonstration) is entirely faked. The script just prints what it _thinks_ would happen. It doesn't actually use the emulator to prove that its thinking is right. Classic Claude being lazy (and the vibe coder not verifying).

I've vibe coded a fix so that the demonstration is actually done properly on the emulator. And also added verification that the 2 line patch actually fixes the bug: https://github.com/juxt/agc-lgyro-lock-leak-bug/pull/1


> you’re reading an AI expansion of someone’s smaller prompt, which contained the original info you’re interested in

This got me thinking: what if LLMs are used to do the opposite? To condense a long prompt into a short article? That takes more work but might make the outcome more enjoyable as it contains more information.


> This got me thinking: what if LLMs are used to do the opposite? To condense a long prompt into a short article? That takes more work but might make the outcome more enjoyable as it contains more information.

You're fighting an uphill battle against the inherent tendency to produce more and longer text. There's also the regression to the mean problem, so you get less information (and more generic) even though the text is shorter.

Basically, it doesn't work



Pangram doesn't reliably detect individual LLM-generated phrases or paragraphs among human written text.

It seems to look at sections of ~300 words. And for one section at least it has low confidence.

I tested it by getting ChatGPT to add a paragraph to one of my sister comments. Result is "100% human" when in fact it's only 75% human.

Pangram test result: https://www.pangram.com/history/1ee3ce96-6ae5-4de7-9d91-5846...

ChatGPT session where it added a paragraph that Pangram misses: https://chatgpt.com/share/69d4faff-1e18-8329-84fa-6c86fc8258...


This is useful, thanks! TIL

Here's one tell-tale of many: "No alarm, no program light."

Another one: "Two instructions are missing: [...] Four bytes."

One more: "The defensive coding hid the problem, but it didn’t eliminate it."


That's just writing. I frequently write like that.

This insistence that certain stylistics patterns are "tell-tale" signs that an article was written by AI makes no sense, particularly when you consider that whatever stylistic ticks an LLM may possess are a result of it being trained on human writing.


These are just some of the good examples I found.

My hunch that this is substantially LLM-generated is based on more than that.

In my head it's like a Bayesian classifier, you look at all the sentences and judge whether each is more or less likely to be LLM vs human generated. Then you add prior information like that the author did the research using Claude - which increases the likelihood that they also use Claude for writing.

Maybe your detector just isn't so sensitive (yet) or maybe I'm wrong but I have pretty high confidence at least 10% of sentences were LLM-generated.

Yes, the stylistic patterns exist in human speech but RLHF has increased their frequency. Also, LLM writing has a certain monotonicity that human writing often lacks. Which is not surprising: the machine generates more or less the most likely text in an algorithmic manner. Humans don't. They wrote a few sentences, then get a coffee, sleep, write a few more. That creates more variety than an LLM can.

Fun exercise: https://en.wikipedia.org/wiki/Wikipedia:AI_or_not_quiz


Here's an alternative way of thinking about this...

Someone probably expended a lot of time and effort planning, thinking about, and writing an interesting article, and then you stroll by and casually accuse them of being a bone idle cheat, with no supporting evidence other than your "sensitive detector" and a bunch of hand-wavy nonsense that adds up to naught.


To start, this is more or less an advertising piece for their product. It's pretty clear that they want to sell you Allium. And that's fine! They are allowed! But even if that was written by a human, they were compensated for it. They didn't expend lots of effort and thinking, it's their job.

More importantly, it's an article about using Claude from a company about using Claude. I think on the balance it's very likely that they would use Claude to write their technical blog posts.


> They didn't expend lots of effort and thinking, it's their job.

Your job doesn't require you to think or expend effort?


While I agree with the sentiment, using AI to write the final draft of the article isn’t cheating. People may not like it, but it’s more a stylistic preference.

Yet another way the mere possibility of AI/LLM being involved diminishes the value of ALL text.

If there is constant vigilance on the part of the reader as to how it was created, meaning and value become secondary, a sure path to the death of reading as a joy.


Those aren’t good examples - that’s just LLMs living for free in your head.

I am reminded of the Simpsons episode in which Principal Skinner tries to pass off the hamburgers from a near-by fast food restaurant for an old family recipe, 'steamed hams,' and his guest's probing into the kitchen mishaps is met with increasingly incredible explanations.

I’m so glad the witch hunt has moved on to phrasing so I get less grief for my em dashes.

See also: “I'm Kenyan. I Don't Write Like ChatGPT. ChatGPT Writes Like Me” by Marcus Olang', https://marcusolang.substack.com/p/im-kenyan-i-dont-write-li...

For what it’s worth, Pangram reports that Marcus’ article is 100% LLM-written: https://www.pangram.com/history/640288b9-e16b-4f76-a730-8000...


In theory, wouldn't be too hard be to settle the question if whether he used ChatGPT to write it: get Olang to write a few paragraphs by hand, then have people judge (blindly) if it's the same style as the article. Which one sounds more like ChatGPT.

When people judge blindly, the are more likely to think the human is the AI and the AI is the human.

73% judged GPT 4.5 (edit: had incorrectly said 4o before)to be the human.

https://arxiv.org/abs/2503.23674

Not only are people bad at judging this, but are directionally wrong.


The times I've written articles, and those have gone through multiple rounds of reviews (by humans) with countless edits each time, before it ends up being published, I wonder if I'd pass that test in those cases. Initial drafts with my scattered thoughts usually are very different from the published end results, even without involving multiple reviewers and editors.

I hate that I can’t write em dashes freely anymore without people accusing the writing of being AI generated.

Even though they are perfect for usage in writing down thoughts and notes.


One thing you can try⸺admittedly it's not quite correct⸺is replacing them with a two-em dash. I've never seen an AI use one, and it looks pretty funky.

Since the advantage of standards is that there are so many to choose from, one lesser-used but still regionally acceptable approach (e.g. https://www.alberta.ca/web-writing-style-guide-punctuation#j...) is to use en-dashes offset with spaces.

I have nothing against em dashes. As long as your writing is human, experienced readers will be able to tell it's human. Only less experienced ones will use all or nothing rules. Em dashes just increase the likelihood that the text was LLM generated. They aren't proof.

That nuance is lost on the majority of anti-AI folks who’ve learned they get positive social reactions by declaring essentially everything to be AI written and condemnable.

“An em dash… they’re a witch!”… “it’s not just X, it’s Y… they’re a witch!”


> anti-AI folks who’ve learned they get positive social reactions by declaring essentially everything to be AI written and condemnable.

that's a strawman alright; all the comments complaining how they can't use their writing style without being ganged up on are positive karma from my angle, so I'm not sure the "positive social reactions" are really aligned with your imagination. Or does it only count when it aligns with your persecution complex?


You have the same problem apparently. You think it’s okay to go witch hunting and accuse people with no real evidence.

Evidently there are no experienced readers who post AI accusations.

Why do you care what others accuse you of?

This is my exact writing style - I'm screwed.

I doubt you write like that. Where can I find your writing other than your comments which IMO don't read like the blog post?

Justify your doubt.

"Here’s how the bug might have manifested."

This is just writing; terse maybe and maybe not grammatically correct, but people write like that.

It's not just terseness, it's the rhythm and "it's not x, it's y".

In fact, the latter is the opposite of terseness. LLMs love to tell you what things are not way more than people do.

See https://www.blakestockton.com/dont-write-like-ai-1-101-negat...

(The irony that I started with "it's not just" isn't lost on me)


> (The irony that I started with "it's not just" isn't lost on me)

But an LLM wouldn't write "It's not just X, it's the Y and Z". No disrespect to your writing intended, but adding that extra clause adds just the slightest bit of natural slack to the flow of the sentence, whereas everything LLMs generate comes out like marketing copy that's trying to be as punchy and cloying as possible at all times.


The AI figures of speech make for painful reading. I don't want to read dozens of examples of what something is not. Just say what it is.


The text reminded me of LinkedInfluencer style. I kept waiting for the "keep hustling/grinding" exhortation.


Currently, as long as you're logged in, npm will not ask for password nor 2FA token for anything. You can change email, generate tokens, add/remove 2FA at will.

Incidentally, email bombing was likely used in the axios attack to bury some important security notifications: https://github.com/axios/axios/discussions/10612

`npm install` might be enough to pull it, unless you pin down to the patch?

I don't think that's right if it's in your package-lock it wouldn't pull it unless you npm update axios, or delete the package-lock.json and then npm install.

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

Search:

HN For You