Hacker News Reader

Comment by bryancoxwell | Hacker News Reader

Find it interesting that the section about LLM’s tells when using it for writing is absolutely littered with emdashes

To be fair, LLMs usually use em-dashes correctly, whereas I think this document misuses them more often than not. For example:

> This can be extraordinarily powerful for summarizing documents — or of answering more specific questions of a large document like a datasheet or specification.

That dash shouldn't be there. That's not a parenthetical clause, that's an element in a list separated by "or." You can just remove the dash and the sentence becomes more correct.

LLMs also generally don't put spaces around em dashes — but a lot of human writers do.

I think you're thinking of british-style "en-dashes" – which is often used for something that could have been separated by brackets but do have a space either side – rather than "em" dashes. They can also be used in a similar place as a colon – that is to separate two parts of a single sentence.

British users regularly use that sort of construct with "-" hyphens, simply because they're pretty much the same and a whole lot easier to type on a keyboard.

I don't know whether that use of the em-dash is grammatically correct, but I've seen enough native English writers use it like that. One example is Philip K Dick.

Perhaps you have—or perhaps you've seen this construction instead, where (despite also using "or") the phrase on the other side of the dash is properly parenthetical and has its own subject.

You can stop LLMs from using em-dashes by just telling it to "never use em-dashes". This same type of prompt engineering works to mitigate almost every sign of AI-generated writing, which is one reason why AI writing heuristics/detectors can never be fully reliable.

This does not work on Bryan, however.

I guess, but if even in you set aside any obvious tells, pretty much all expository writing out of an LLM still reads like pablum without any real conviction or tons of hedges against observed opinions.

"lack of conviction" would be a useful LLM metric.

I ran a test for a potential blog post where I take every indicator of AI writing and tell the LLM "don't do any of these" and resulted in high school AP English quality writing. Which could be considered a lack of conviction level of writing.

I believe Bryan is a well known em dash addict

And I mean no disrespect to him for it, it’s just kind of funny

>I believe Bryan is a well known em dash addict

I was hoping he'd make the leaderboard, but perhaps the addiction took proper hold in more recent years:

https://www.gally.net/miscellaneous/hn-em-dash-user-leaderbo...

https://news.ycombinator.com/user?id=bcantrill

No doubt his em dashes are legit, of course.

There was a comment recently by HN's most enthusiastic LLM cheerleader, Simon Willison, that I stopped reading almost immediately (before seeing who posted it), because it exuded the slop stench of an LLM: https://news.ycombinator.com/item?id=46011877

However, I was surprised to see that when someone (not me) accused him of using an LLM to write his comment, he flatly denied it: https://news.ycombinator.com/item?id=46011964

Which I guess means (assuming he isn't lying) if you spend too much time interacting with LLMs, you eventually resemble one.

> if you spend too much time interacting with LLMs, you eventually resemble one

Pretty much. I think people who care about reducing their children's exposure to screen time should probably take care to do the same for themselves wrt LLMs.

I don't know what to tell you: that really does not read like it was written by a LLM. You were perhaps set off by the very first sentence, which sounds like it was responding to a prompt?

It reads exactly like all his writing over many years afaict. Which is to say - it reads well. Just because someone is clear, thoughtful, and thorough, does not make them an AI. AI writing is actually quite different to this.

Reply on news.ycombinator.com