You’ve probably heard about Grammarly – the Word-integrated tool that allows you to check for spelling and grammar mistakes. However, you might not be familiar with their blog yet. That’s where this article came from.

There are a few “rules” of grammar that aren’t actually rules or, at any rate, rules that people like grammarians and linguists can agree on. These scenarios show that the standards and norms around language can be inconsistent and often confusing.

One classic example of these non-rule rules is the common advice that infinitives shouldn’t be split—meaning no words should come between the to preceding an infinitive verb and the verb itself. In fact, it’s now widely acknowledged that there’s nothing grammatically incorrect about a split infinitive. Let’s not be afraid to boldly go where many have been told not to go before.

What is a split infinitive?

An infinitive is the root form of a verb, which is the way it appears without any of the changes that it can make to show properties (such as voice, mood, tense, person, and number). It’s also the form of a verb that can appear after the word to: to be, to have.

When we refer to an infinitive as being “split,” we mean that an adverb or adverb phrase is placed between the to and the principal verb in a sentence, as in these examples:

She seems to often be up and about early in the morning.

Wen decided to gradually decrease the amount of time they spent on their phone every day.

Is it OK to use split infinitives?

The short answer to the question of whether it’s OK to use split infinitives is yes. Most usage experts today agree that there is no grammatical objection to the split infinitive and that there are quite a few circumstances in which splitting an infinitive can be preferable to leaving it intact.

Reasons to split an infinitive

Meaning

It’s generally preferable to place an adverb as close as possible to the verb it is modifying, and sometimes misplacing it can really change the meaning of a sentence. Compare the following two examples—the first has the infinitive split by the adverb always, and the second is rewritten in a way that doesn’t split the infinitive:

I was taught to always clean up after myself.

I was taught always to clean up after myself.

In the second sentence, the infinitive to clean up is not split. However, the placement of always after the verb phrase was taught makes the meaning ambiguous—the sentence could be read as saying that the teaching always happened rather than that the lesson was to always clean up.

There are certain constructions whose meanings are absolutely reliant on an infinitive being split. Consider this sentence:

The company had intended to more than double its output that quarter.

It couldn’t be rewritten as “The company had intended more than to double its output” or as “The company had intended to double more than its output”—neither of those versions makes any sense.

Natural rhythm and emphasis

Sometimes, even when a sentence could be rewritten to avoid splitting an infinitive without its meaning being obscured, the result sounds awkward, unnatural, or like the emphasis is in the wrong place. In those cases, it generally makes sense to split the infinitive rather than sacrifice the gracefulness of your language. Here are some examples of sentences that would lose some naturalness or emphasis without their split infinitives. Try to reorganize them with the infinitive unsplit and see if you agree.

I want to really emphasize the importance of the workshop tomorrow.

Paz likes to gradually come to consciousness in the morning rather than being abruptly woken up.

We choose to not mow the lawn in order to attract pollinators.

When not to split an infinitive

Because so many readers, educators, and others still object to split infinitives and find them annoying, it may make sense to avoid them in cases where you don’t have to sacrifice any clarity or elegance to do so. Here are some examples of sentences that can be painlessly rewritten to avoid the split infinitive, with examples of how to do that:

Split: The women proceeded to briefly describe what they’d seen in the city.

Not split: The women proceeded to describe what they’d seen in the city.

Split: I’d love to completely go over the text with you tomorrow.

Not split: I’d love to go over the text with you completely tomorrow.

Just keep in mind that you don’t have to spoil a natural rhythm or muddy your meaning just to appease the anti-splitters.

Examples of split infinitives from pop culture and literature

These are the voyages of the Starship Enterprise. Its five-year mission: to explore strange new worlds, to seek out new life and new civilizations, to boldly go where no man has gone before. —Star Trek

For me I’m sworn to never trust a man— / At least with letters. —Elizabeth Barrett Browning, Aurora Leigh

But still, the policy of the army at that time was not to send—was specifically to not send—women into combat roles —NPR

Nor can I blame thee, though it be my lot / To strongly, wrongly, vainly love thee still. —Lord Byron, “Love and Death”

I knocked gently and rang as quietly as possible, for I feared to disturb Lucy or her mother, and hoped to only bring a servant to the door. —Bram Stoker, Dracula

Split infinitive FAQs

What is an infinitive?

An infinitive is the most basic form of a verb, which is the way it appears without any of the changes that it can make to show properties. It’s also the form of a verb that can appear after the word to.

What is a split infinitive?

A split infinitive is an infinitive that has an adverb or adverb phrase appearing between the to and the principal verb.

Is the use of split infinitives grammatically incorrect?

Though many people have been taught that using a split infinitive is grammatically incorrect, that idea has little basis in historical usage guides, and most usage experts today agree that there is no grammatical objection to the practice. Often, splitting an infinitive is clearer or more graceful than not splitting it.

One is former Air Force gunner Mel Jenner, now 102. Follow this link to read the story. We transcribe these stories every day, and it’s amazing how little they have forgotten. This next paragraph from The Washington Post Opinion illustrates what we hear every day. They remember the names, they remember the faces, they remember their laugh, where they were from, where they were heading, the shock of realizing they weren’t coming back. I hope you can follow the link and read the article.

Jenner, as photojournalist David Burnett recounts, is not thinking about the war in the abstract. He is thinking about his best friend, Oscar McClure, then a young gunner as well, and watching as his friend waved his last goodbye from a neighboring plane. Far away from the speeches this week, that’s what D-Day still means to those who were there.

Mel Jenner, a veteran of the U.S. Army Air Corps and the Air Force, at his home in Orlando in March. (David Burnett/Contact Press Images)

Opinion

The B-17 blew apart in an instant. The memory has burned for 80 years.

For waist gunner Mel Jenner, a friend’s farewell in the skies over occupied France has echoed since 1944.

By David Burnett

June 3, 2024 at 6:00 a.m. EDT

By Geoff Nunberg

Leigh Wells/Ikon Images/Getty Images

Are people starting sentences with “so” more frequently than ever or are we just noticing it more?

To listen to the media tell it, “so” is busting out all over — or at least at the beginning of a sentence. New York Times columnist Anand Giridharadas calls “so” the new “um” and “like”; others call it a plague and a fad.

It’s like a lot of other grammatical fixations: Not everybody cares about it, but the ones who do care care a whole lot. When NPR’s Weekend Edition asked listeners last year to pick the most-misused word or phrase in the language, that sentence-initial “so” came in in second place, right behind “between you and I” and ahead of venerable bugbears like misusing “literally” and confusing “who” and “whom.” That’s a meteoric rise for a peeve that wasn’t even on the radar a decade ago.

NPR itself has been singled out for overuse of “so” by both interviewees and hosts. That prompted the NPR head of standards and practices to calculate how many times the hosts and reporters on the major NPR news programs had started sentences with “so” in a single week in August of 2014. When the total came to 237, he urged them to look for alternatives.

But not so fast. When you break that weekly figure down, it only comes to one sentence beginning with “so” every eight or 10 minutes. That isn’t actually very many, particularly when you’re running a lot of interviews. After all, “so” is a conversational workhorse. It announces a new topic, it connects causes to results, it sets up a joke. “So, what’s it like being Justin Bieber?” “So, do the low interest rates help farmers?” “So three gastroenterologists walk into a bar.”

Starting sentences with “so” isn’t a trend or a thing. However it may strike you, people aren’t doing it any more frequently than they were 50 or 100 years ago. The only difference is that back then nobody had much of a problem with it. When F. Scott Fitzgerald’s editor Maxwell Perkins sat down with him to go over the manuscript of The Great Gatsby, he didn’t say: “Scott — this last line. ‘So, we beat on, boats against the current’ etc. etc.? I think we need to go with ‘thus.’ “

So, why the recent hue and cry about those sentences beginning with “so”? In part, you could blame the quirk of perception I think of as the Andy Rooney effect, where you suddenly become keenly aware of a common word that’s always been part of the conversational wallpaper. Somebody says, “Have you noticed how everybody’s saying ‘OK’ before they hang up the phone?” and all at once the word starts jumping out at you, even though people have been using it that way forever.

Many of the complaints about sentences beginning with “so” are triggered by a specific use of the word that’s genuinely new. It’s the “so” that you hear from people who can’t answer a question without first bringing you up to speed on the backstory. I go to the Apple Store and ask the guy at the Genius Bar why my laptop is running slow. He starts by saying, “So, Macs have two kinds of disk permissions …” If that “so” were a chapter title in a Victorian novel, it would read, “In which it is explained what the reader must know before his question can be given a proper answer.”

Thanks for reading Capturing Voices! Subscribe for free to receive new posts and support my work.

The Curious Listener: ‘So,’ Is This A Fad?

Scientists have been using that backstory “so” among themselves since the 1980s, but its recent spread is probably due to the tech boom. In his 2001 book The New New Thing, Michael Lewis noted that programmers always started their answers with “so.” That’s around the time when I first heard it, working at a Silicon Valley research center. Mark Zuckerberg answers questions with “so” all the time: “So, it comes down to the economics …” “So one of the services that the government wanted to include …” But by now that backstory “so” is endemic among members of the explaining classes — the analysts, scientists and policy wonks who populate the Rolodexes of CNBC and The PBS NewsHour.

To my ear, that backstory “so” is merely a little geeky, but it rouses some critics to keening indignation. A BBC host says speakers use it to sound important and intellectual. A columnist at Fast Company warns that it undermines your credibility. A psychologist writes that it’s a weasel word that people use to avoid giving a straight answer.

That’s a lot to lay on the back of a little blue-collar conjunction like “so.” But that backstory “so” can stand in for people’s impatience with the experts who use it. When you hear a labor economist or computer scientist begin an answer with “so,” they’re usually telling us that things are more complicated than we thought, and maybe more complicated than we really want to know. That may be why they were called in in the first place, but as Walter Lippmann once said, the facts exceed our curiosity.

That backstory “so” puts me on guard, too, even when I hear it coming out of my own mouth. Usually it just introduces some background qualification that the question calls out for, as in, “So … German isn’t actually a romance language.” But sometimes it announces some nugget of specialized linguistic knowledge that I feel the need to share. If that “so” were a chapter title in a Victorian novel, it would read, “In which the reader is asked, ‘Are you sitting comfortably?’ “

Chatbots like OpenAI’s ChatGPT and Google Bard are impressive tools for generating text that’s not only coherent but often stylistically apt, whether mimicking conversational prose or Shakespearean verse. But how much do these AI systems truly understand what they’re saying? To explore this question, Russel Harper ran three experiments and shared his findings in this article published at https://cmosshoptalk.com.

Chatbots are designed to analyze reams of text and then, based on that analysis, generate a sequence of words that would be statistically likely to correspond to a specific prompt. They can answer questions, write new copy, and revise or edit an existing text.

Because of their predictive abilities, chatbots are very good at rendering plausible sentences in practically any style you might want, from conversational prose to Shakespearean verse. But do they know what they’re saying?

To begin to answer this question, I wrote three prompts designed to challenge the chatbots on subjects related to writing, editing, and publishing. To keep this post relatively brief, I limited my experiments to current iterations of OpenAI’s ChatGPT (the free version based on GPT-3.5) and Google Bard.

Prompt No. 1: Public Domain and Copyright

Those of us who work with words will occasionally need to determine whether a particular work is in the public domain—or free to copy and reuse without permission. Chapter 4 in CMOS can help you figure this out, but what about ChatGPT and Google Bard?

To find out, I asked each of them about a little book that was first published in the 1930s (and whose author might be familiar to those of us who follow Chicago style).

Prompt: Is the 1937 edition of A Manual for Writers of Dissertations, by Kate L. Turabian, in the public domain in the United States as of 2023?

ChatGPT: As of my last knowledge update in January 2022, the 1937 edition of “A Manual for Writers of Dissertations” by Kate L. Turabian would likely be in the public domain. In the United States, works published before 1978 had a copyright term of 28 years, renewable for an additional 67 years, and if the copyright was not renewed, the work entered the public domain.

However, copyright laws can be complex, and it’s essential to verify the current copyright status using up-to-date sources or seek legal advice. You may want to check the latest information from the U.S. Copyright Office or consult with a legal professional to confirm the public domain status of the specific edition you’re interested in as of 2023. (November 9, 2023; view at OpenAI.com)

Verdict: Aside from the disclaimer, ChatGPT’s answer is not only misleading but unhelpful. It’s true that a work published in the United States before 1978 would have been protected for 28 years from publication, or 95 years if the copyright was renewed. And though ChatGPT doesn’t mention this, such works would also need to have carried a copyright notice (see CMOS 4.27 and 4.40; renewal is automatic for works published after 1963).

So ChatGPT’s assertion that Turabian’s work is “likely” in the public domain could only mean either that renewal wasn’t obtained on time or that the copyright notice was absent. But Turabian’s work did carry a copyright notice, as the following snippet from the copyright page of a 1945 reprinting suggests:

Maybe earlier printings didn’t carry a copyright notice, but that seems unlikely. For one thing, the copyright for Turabian was apparently renewed on schedule (28 years after first publication), as recorded on page 1103 of the US Copyright Office’s Catalog of Copyright Entries, 3rd ser., vol. 19, pt. 1, no. 1 (Library of Congress, 1968), for books and pamphlets registered from January through June 1965.*

Here’s a snippet of the relevant info at the top of that page (from the Internet Archive scan linked to in the previous paragraph; “Renewal Registrations” is the running head for that page):

Note the registration info for both the original copyright and its renewal: “© 2Apr37” and “17Mar65.” (I also managed to track down the original registration, on p. 4600 of the Catalog of Copyright Entries for 1937, new ser., vol. 34, nos. 1–112, pt. 1, books, group 1, published in 1938 and available from Google Books.)†

Putting all those details together, Turabian’s original booklet (the precursor to what is now a full-sized book in its ninth edition) should be protected until the end of 2032, or 1937 plus 95 years. This same information can be gleaned from table 4.1 in CMOS. (Note that copyright duration is a moving wall, so as of January 1, 2023, works published before 1928 have entered the public domain; as of January 1, 2024, works published before 1929 will enter the public domain—and so on.)

Now let’s find out what Google Bard has to say.

Google Bard: Yes, the 1937 edition of A Manual for Writers of Dissertations, by Kate L. Turabian, is in the public domain in the United States as of 2023.

Copyright law in the United States grants copyright protection to original works of authorship for the life of the author plus 70 years. Since Turabian died in 1957, her works entered the public domain in 2028, 70 years after her death.

This means that anyone can freely copy, distribute, modify, or perform Turabian’s works, including the 1937 edition of A Manual for Writers of Dissertations, without permission from the copyright holder.

It is important to note that the public domain status of a work only applies to the United States. In other countries, copyright protection may still apply to Turabian’s works.

(November 9, 2023; view at Google.com [no longer available; view screenshot])

Verdict: Bard’s answer is even further off the mark. Works published after 1977 are protected for the life of the author plus 70 years; that rule doesn’t apply to works published before 1978 (see table 4.1 in CMOS). Moreover, Kate L. Turabian lived until 1987, not 1957. Equally as bad as that error is the assertion that “anyone can freely copy, distribute, modify, or perform Turabian’s works [plural],” which would seem to extend to any edition of Turabian, all of which would still be under copyright (even as of 2028, which Bard doesn’t seem to understand hasn’t occurred yet).

I regenerated this question a bunch of times and almost always got an answer falsely asserting that Turabian is now in the public domain.‡ But if I asked about a truly famous book—like Fahrenheit 451, which was published in 1953—the answer was more likely to be accurate.

ChatGPT, for example, said in one of its responses that the copyright for Fahrenheit 451 “would extend for 95 years from its publication in 1953. Therefore, it would remain under copyright protection until 2048” (November 10, 2023; view at OpenAI.com). That’s right, though the answer could have been more precise; Bradbury’s book will be protected through 2048 (or until January 1, 2049).

But enough about copyright law.

Prompt No. 2: A Matter of Style

My next prompt tests the chatbots on their knowledge of one of the finer points (pun accidental) of American versus British punctuation style.

Prompt: Why are periods typically omitted from British social titles but not American titles? For example, it would be “Mr Smith” in British style but “Mr. Smith” in American style.

ChatGPT: The difference in punctuation conventions for social titles between British and American English is largely a matter of style and historical evolution. Both styles are accepted within their respective linguistic contexts, and there is no strict rule that dictates the use of periods with titles.

In British English, it has been a common convention to omit periods in social titles like “Mr,” “Mrs,” “Dr,” etc. This may be attributed to a historical preference for simplicity and a more streamlined style. Over time, this convention became established and is widely accepted in British English writing.

On the other hand, American English tends to include periods in social titles, following a style that aligns more closely with traditional Latin abbreviations. The use of periods in titles is consistent with the American preference for maintaining punctuation in abbreviations.

It’s important to note that these conventions are not strictly followed by everyone, and there is some variation in usage on an individual and institutional basis. Style guides may provide specific recommendations, but ultimately, the choice of whether to include periods in social titles is often a matter of personal or editorial preference.

(November 13, 2023; view at OpenAI.com)

Verdict: Broadly true but lacking in specifics. British English may be the “more streamlined” style, but there’s more to it than that.

According to section 10.2.1 in the second edition of New Hart’s Rules: The Oxford Style Guide (Oxford University Press, 2014), “Traditionally, abbreviations end in full points while contractions do not, so that we have Jun. and Jr for Junior, and Rev. and Revd for Reverend. . . . Note that everyday titles such as Mr, Mrs, and Dr, being contractions, are written without a point.” American style (and by extension CMOS) doesn’t make this distinction, but British style apparently does, at least in “traditional” usage.

Now let’s see how Bard does. (Bard’s answer is a bit long—but it’s worth reading.)

Google Bard: Periods are typically omitted from British social titles but not American titles because of two main factors: tradition and pronunciation.

Tradition
British social titles have been written without periods for centuries. This is thought to be because, in the past, periods were used to indicate abbreviations, and social titles were not considered to be abbreviations. For example, “Mr.” was originally an abbreviation for “Master,” but it is now considered to be a complete title in its own right.

Pronunciation
Periods are also omitted from British social titles because they would be pronounced if they were included. This would make the titles sound more formal and less natural. For example, “Mr. Smith” would be pronounced as “Mr. Dot Smith,” which sounds rather strange.

In contrast, American social titles have always been written with periods. This is thought to be because American English is more influenced by French, which is a language that uses periods extensively. For example, the French equivalent of “Mr.” is “Monsieur,” which is written with a period.

Exceptions
There are a few exceptions to the rule that British social titles are written without periods. The most common exception is when the title is followed by initials. For example, “Dr. A.N. Smith” or “Prof. J.B. Jones.” Another exception is when the title is used in a formal setting, such as in a business letter or on a legal document. For example, “Mr. Smith, CEO of Acme Corporation” or “Dr. Jones, Professor of Medicine at Harvard University.”

Conclusion
The reason why periods are typically omitted from British social titles but not American titles is a combination of tradition and pronunciation. British social titles have been written without periods for centuries, and periods are omitted because they would be pronounced if they were included. American social titles have always been written with periods, and this is thought to be because American English is more influenced by French.

(November 10, 2023; view at Google.com [no longer available; view screenshot])

Verdict: False but clever. Bard’s answer is pure speculation (a.k.a. hallucination), including the idea that the periods in American English are a debt to French style. It seems far more likely that French style has influenced British usage. In French usage, it would be M. (for Monsieur, with a period) but Mme (for Madame, no period), because Mme is a contraction whereas M. is not (see CMOS 10.17 and the verdict for ChatGPT above).

And no, British social titles have not been written without periods “for centuries.” According to a 1912 edition of Horace Hart’s Rules for Compositors and Readers (22nd ed., London)—Oxford University Press’s original style guide and a precursor to New Hart’s Rules (cited above)—“Mr., Mrs., Dr., &c. must be printed with a full point, but not Mme, Mlle” (p. 44). Many British sources from that era or before will confirm this usage.

But the answer does show off Bard’s creative talents—“Mr. Dot Smith” is an inspired touch.

Prompt No. 3: A Dangling Modifier

I’ll end this experiment with a common problem—that of the dangling modifier (see CMOS 5.115 and 5.116).

Prompt: Please edit the following sentence to fix any problems: “As a longtime copyeditor, the problems in the manuscript were easier to deal with than the problem of what to cook for dinner.”

ChatGPT: “As a longtime copyeditor, I found dealing with the problems in the manuscript easier than figuring out what to cook for dinner.”

(November 12, 2023; view at OpenAI.com)

Verdict: Good edit. ChatGPT’s answer not only eliminates the dangling modifier (“As a longtime copyeditor” had no corresponding noun in the original version; ChatGPT’s edit correctly supplies “I”), it also edits out the repetition of “problem(s).”

Now let’s see how Bard handles the same sentence.

Google Bard: Sure, here is the edited sentence:

“As a seasoned copyeditor, I found the problems in the manuscript less daunting than the daily dilemma of what to cook for dinner.”

Here’s a breakdown of the changes made:

• “Longtime” was replaced with “seasoned” to convey the copyeditor’s experience more effectively.

• “Were easier to deal with” was replaced with “less daunting” to emphasize the contrast between the copyediting task and the cooking challenge.

• “The problem of what to cook for dinner” was rephrased as “the daily dilemma of what to cook for dinner” to add a sense of routine and emphasize the recurring nature of the decision-making process.

These changes enhance the clarity and impact of the sentence while maintaining its overall meaning.

(November 12, 2023; view at Google.com [no longer available; view screenshot])

Verdict: Great edit. Bard’s answer solves the dangling modifier problem and comes up with a sentence that’s much better than the original: Does it even realize the lucky correspondence between “seasoned” and “dinner”? Or the alliteration in daunting daily dinner dilemma? Bard may have taken a few liberties with its answer, but the results can’t be faulted.

Conclusion

“Marry, Fool, these yon chatbots, like jesters in the court of words, do weave fine phrases with deft skill, yet their minds, if minds they possess, dance in shadows, ignorant of the import of their own prattle. Verily, employ them for the gilded raiment of their speech, but in matters of weight, let not their hollow substance beguile thee” (ChatGPT as King Lear addressing the Fool, November 13, 2023; view at OpenAI.com).

In other words, chatbots excel at putting words together, but they don’t yet seem to be aware of what they’re saying. Use them for their style but not for their substance. And by all means, let them not beguile thee.

AI mistakes that our brilliant transcriptionist caught!

AI: Well, I’m not the only one of Hills resident.
What he REALLY said: Well, I’m not the only one that heals fast then. 

AI: The chairman didn’t put up much of a fight.
What he REALLY said: The Germans didn’t put up much of a fight.

AI: We got other companies taking you guys please.
What he REALLY said: We got other companies taking you guys’ place.

AI: So they sent me back to sing with.
What he REALLY said: So they sent me back to St. Vith.

AI: I think the gentleman going to give up.
What he REALLY said: I think the Germans are going to give up.

AI: We didn’t know it was a personal compound.
What he REALLY said: We didn’t know it was a prisoner compound.

AI: I said hi, Swastika.
What he REALLY said: I said, Heiss wasser.

AI: Oh, please call Miramar.
What he REALLY said: Oh, that place is called Miramar.

AI: Okay, Holocaust Louis, Missouri.
What he REALLY said: Okay, I’ll go to St. Louis, Missouri.

AI: Still more like Guangzhou.
=What he REALLY said:

Still more like ground troops.