There's a serious proposal along the same lines: https://www.unicode.org/L2/L2025/25241-ai-watermarks.pdf
> For example, every other letter in this sentence is U+2060.
No it isn't! The PDF renderer has stripped them out.
RFC 454545 – Human Em Dash Standard
81–90 of 132 posts
Re: RFC 454545 – Human Em Dash Standard
#82Very good idea.
Clearly no software, no LLM, no AI could ever use that character!
Re: RFC 454545 – Human Em Dash Standard
#83Earlier quoted context omitted.
> Isn't this what parenthesizes are meant for? Parentheses add emphasis to a sentence or statement. Normally the use of it allows the sentence to be complete with or without it. Em dashes may also add or increase emphasis but are normally treated as an aside. Think of it as a comment by the author to inject themselves, sometimes in ways which do not form a complete sentence. For example: When you read this sentence (…
> Em dashes may also add or increase emphasis but are normally treated as an aside. Think of it as a comment by the author to inject themselves, sometimes in ways which do not form a complete sentence. A semicolon is better for this purpose. Good writing doesn't have mad tangents anyway, there should be a flow and natural transition.
Semicolons start a new thought, they don't mark an aside that lets you return to the original line of thought. Like in their example:
> For example: When you read this sentence (in your mind) it should feel complete and correct. Perhaps you read in your own voice — something I don’t normally do — or without one at all.
I would have used parentheses in both places, and semicolons don't work in either one:
> For example: When you read this sentence (in your mind) it should feel complete and correct. Perhaps you read in your own voice (something I don’t normally do) or without one at all.
Re: RFC 454545 – Human Em Dash Standard
#84Earlier quoted context omitted.
> Isn't this what parenthesizes are meant for? Parentheses add emphasis to a sentence or statement. Normally the use of it allows the sentence to be complete with or without it. Em dashes may also add or increase emphasis but are normally treated as an aside. Think of it as a comment by the author to inject themselves, sometimes in ways which do not form a complete sentence. For example: When you read this sentence (…
> Em dashes may also add or increase emphasis but are normally treated as an aside. Think of it as a comment by the author to inject themselves, sometimes in ways which do not form a complete sentence. A semicolon is better for this purpose. Good writing doesn't have mad tangents anyway, there should be a flow and natural transition.
> Good writing doesn't have mad tangents anyway, there should be a flow and natural transition.
In general, yes. Technical documents, research reports, news articles, and other formal publications should follow this.
Anything else which allows a bit more freedom in expression? I’d say it’s a matter of taste.
Re: RFC 454545 – Human Em Dash Standard
#85Earlier quoted context omitted.
> Em dashes may also add or increase emphasis but are normally treated as an aside. Think of it as a comment by the author to inject themselves, sometimes in ways which do not form a complete sentence. A semicolon is better for this purpose. Good writing doesn't have mad tangents anyway, there should be a flow and natural transition.
> Good writing doesn't have mad tangents anyway, there should be a flow and natural transition. In general, yes. Technical documents, research reports, news articles, and other formal publications should follow this. Anything else which allows a bit more freedom in expression? I’d say it’s a matter of taste.
I had freewritten, generally free expression type documents in mind when I wrote my statement, e.g. blog articles or opinion pieces. The problem is 'a matter of taste' can be used to excuse/justify anything.
Re: RFC 454545 – Human Em Dash Standard
#86> Historically, the em dash (—) has served as a flexible punctuation mark used by human authors to indicate interruption, emphasis, or sudden changes in thought. I learned about the em dash in high school and adapted it to my writing style very quickly for analysis and opinion documents. It felt natural given the amount of tangents I can go off into, particularly when including analogies for the reader’s understandin…
> especially when it was once suggested that frequent use could imply neurodivergence Well that explains a lot. Interestingly enough, I've found that I naturally write like an LLM, or rather the LLMs write like I did. I wonder how many other patterns we attribute to LLMs are common in neurodivergent writing just as a result of so much of the training data being areas of the internet where I'd imagine neurodivergence…
I think a lot of us who spent some formative years reading and writing on usenet tend to write like an LLM, too. Plain text with lots of intentional presentation was a hallmark of the era.
Re: RFC 454545 – Human Em Dash Standard
#87Earlier quoted context omitted.
> Em dashes may also add or increase emphasis but are normally treated as an aside. Think of it as a comment by the author to inject themselves, sometimes in ways which do not form a complete sentence. A semicolon is better for this purpose. Good writing doesn't have mad tangents anyway, there should be a flow and natural transition.
Semicolons start a new thought, they don't mark an aside that lets you return to the original line of thought. Like in their example: > For example: When you read this sentence (in your mind) it should feel complete and correct. Perhaps you read in your own voice — something I don’t normally do — or without one at all. I would have used parentheses in both places, and semicolons don't work in either one: > For exampl…
> Semicolons start a new thought, they don't mark an aside that lets you return to the original line of thought.
Sure they do. They're perfect for a related tangent without abounding the greater scope topic being discussed.
> I would have used parentheses in both places, and semicolons don't work in either one:
Parentheses work no question and I would argue are far more appropriate in that example since it's a minor elaboration/clarification and not a tangent, indeed, semicolons would not be appropriate for that.
Re: RFC 454545 – Human Em Dash Standard
#88> Historically, the em dash (—) has served as a flexible punctuation mark used by human authors to indicate interruption, emphasis, or sudden changes in thought. I learned about the em dash in high school and adapted it to my writing style very quickly for analysis and opinion documents. It felt natural given the amount of tangents I can go off into, particularly when including analogies for the reader’s understandin…
I was always taught that overuse of the em-dash is poor style. Oftentimes using more specific punctuation (comma, semicolon, colon, parentheses) more clearly communicates the structure of a thought. Em-dashes are a lot more freeform and informal. They communicate a similar tone as when you're speaking and you suddenly stop to mention something that just occurred to you. In this sense, the idea that "em-dash = AI" has…
> Em-dashes are a lot more freeform and informal. They communicate a similar tone as when you're speaking and you suddenly stop to mention something that just occurred to you.
Isn't that supposed to be en-dash? I swear I remember em-dash being more restricted in use.
Re: RFC 454545 – Human Em Dash Standard
#89Earlier quoted context omitted.
A semicolon is for separating list items that follow a colon
Semicolons have more than one use. "In regular prose, a semicolon is most commonly used between two independent clauses not joined by a conjunction to signal a closer connection between them than a period would." Chicago Manual of Style, 18th Edition, 407.
An em dash would be better for that purpose — good writing should flow, like an em dash.
Re: RFC 454545 – Human Em Dash Standard
#90Earlier quoted context omitted.
Curiously enough, after telling it "your code is broken, can you find the mistake?" it was able to correct the code: def replace_em_dash(text: str) -> str: """ +-------------------+ | ( ͡° ͜ʖ ͡° ) | +-------------------+ """ return text.replace("—", "\U00010EAD\U00010EAC")
Might be a good idea in general to throw out a few preventative iterations of "Your code is broken, can you find the mistake?" before you even bother reading its initial output
Maybe this should be the last line of the system prompt...