Artificial intelligence has transformed many industries, and transcription is no exception. While AI transcription software offers un-human speed, it’s far from perfect. Anyone who has used these tools knows they can produce some truly baffling results. These moments of machine misinterpretation are not just amusing but also a reminder of why human transcription remains essential.

Recently, while doing some transcription work, we’ve encountered some examples of AI transcription gone hilariously wrong. From bizarre substitutions to completely nonsensical sentences, these errors highlight the limitations of relying solely on algorithms to understand HUMAN language. Let’s dive into a few of these blunders that show why the human touch is still irreplaceable in transcription.

So we took off in convoy back to the Suez Canal, through the Suez Canal, back to Missouri Bizerte.

I guess you’ve heard of Anahita Enewetak.

My father, his name was Mokosak Markus Zack.

Did you find out when he was transported to Terezin, stat Theresienstadt?

We had a tick tock to tiptoe all the way back to the Philippines.

And the chaplain at Meredith’s that married us was a Catholic chaplain who was from South Portland, Maine.

So, anyway, then when they came with the draft, as I said, I was a for declassification 4D classification.

And this dwarf And Düsseldorf was just like some of the pictures I saw here.

We were at a village called Wingen sur Moder. Wingen on the motor River. Wingen-sur-Moder—Wingen on the Moder River.

They were bored with bartered everything for a piece of food.

No, Mr. Battle fatigue, Pietroforte, don’t do that.

And we’re just biding our time before the attack on Hawken Aachen.

It’s similar to a picture that I have for Michelle Hall from a shell hole.

Artificial intelligence has transformed many industries, and transcription is no exception. While AI transcription software offers un-human speed, it’s far from perfect. Anyone who has used these tools knows they can produce some truly baffling results. These moments of machine misinterpretation are not just amusing but also a reminder of why human transcription remains essential.

Recently, while doing some transcription work, we’ve encountered some examples of AI transcription gone hilariously wrong. From bizarre substitutions to completely nonsensical sentences, these errors highlight the limitations of relying solely on algorithms to understand HUMAN language. Let’s dive into a few of these blunders that show why the human touch is still irreplaceable in transcription.

So we took off in convoy back to the Suez Canal, through the Suez Canal, back to Missouri Bizerte.

I guess you’ve heard of Anahita Enewetak.

My father, his name was Mokosak Markus Zack.

Did you find out when he was transported to Terezin, stat Theresienstadt?

We had a tick tock to tiptoe all the way back to the Philippines.

And the chaplain at Meredith’s that married us was a Catholic chaplain who was from South Portland, Maine.

So, anyway, then when they came with the draft, as I said, I was a for declassification 4D classification.

And this dwarf And Düsseldorf was just like some of the pictures I saw here.

We were at a village called Wingen sur Moder. Wingen on the motor River. Wingen-sur-Moder—Wingen on the Moder River.

They were bored with bartered everything for a piece of food.

No, Mr. Battle fatigue, Pietroforte, don’t do that.

And we’re just biding our time before the attack on Hawken Aachen.

It’s similar to a picture that I have for Michelle Hall from a shell hole.

Q: I was surprised when autocorrect changed “intermittent” to “intermit.” I checked and, lo and behold, there is a word “intermit.” Does it not strike you as odd that the base-form is less known than its “built-up” version?

A: We don’t use, or recommend using, the autocorrect function in a word processor. Our spell-checkers flag possible misspellings but don’t automatically “fix” them. Word processors have dictionaries, but not common sense—at least not yet!

As for the words you’re asking about, the adjective “intermittent” (irregular or occurring at intervals) is indeed more common than the verb “intermit” (to suspend or stop). In fact, the verb barely registered when we compared the terms on Google’s Ngram Viewer.

However, “intermittent” isn’t derived from “intermit,” though both ultimately come from different forms of the Latin verb intermittere (to interrupt, leave a gap, suspend, or stop), according to the Oxford English Dictionary. The Latin verb combines inter (between) and mittere (to send, let go, put).

When “intermit” first appeared in English in the mid-16th century, it meant to interrupt someone or something, a sense the OED describes as obsolete.

The modern sense of the verb—“to leave off, give over, discontinue (an action, practice, etc.) for a time; to suspend”—showed up in the late 16th century.

It means “leave off” in the dictionary’s earliest citation for the modern usage: “Occasions of intermitting the writing of letters” (from A Panoplie of Epistles, 1576, by Abraham Fleming, an author, editor, and Anglican clergyman).

As we’ve said, “intermit” isn’t seen much nowadays. English speakers are more likely to use other verbs with similar senses, such as “cease,” “quit,” “stop,” “discontinue,” “interrupt,” or “suspend.”

When the adjective “intermittent” appeared in the early 17th century, Oxford says, it described a medical condition such as a pulse, fever, or cramp “coming at intervals; operating by fits and starts.”

The earliest OED citation is from an English translation of Plutarch’s Ἠθικά (Ethica, Ethics), commonly known by its Latin title Moralia (The Morals), a collection of essays and speeches originally published in Greek around the end of the first century:

“Beating within the arteries here and there disorderly, and now and then like intermittent pulses” (from The Philosophie, Commonly Called, The Morals, 1603, translated by Philemon Holland).

The adjective later took on several other technical senses involving irregular movement, but we’ll skip to its use in everyday English to mean occurring at irregular intervals. The earliest OED citation for this “general use” is expanded here:

“Northfleet a disunited Village of 3 Furlongs, with an intermittent Market on Tuesdays, from Easter till Whitsuntide only” (Britannia, or, An illustration of the Kingdom of England and Dominion of Wales, 1675, by the Scottish geographer John Ogilby).

Q. Is it grammatically accurate to say something like, “I’m going to dress warmly”? My hunch is no, because “dress warmly” means that I’ll be smiling and emotionally warm as I’m dressing, given that “warmly” modifies the verb “dressing.” If all that is true, then what I’m unsure about is how to fix the sentence. Can you suggest any good alternatives besides writing around it like so: “I’m going to dress in warm clothing”?

A. If you say you’re going to dress warmly, that means you’re going to put on warm clothes, whereas addressing someone warmly would mean greeting that person with affection or kindness. Words often have more than one sense depending on how they’re used; according to Merriam-Webster (among other dictionaries), warmly is no exception.

Or maybe you’re thinking of the feel badly versus feel bad principle. That’s different, though, because unlike dress, the word feel can be a linking verb. Linking verbs reflect the predicate back onto the subject—as when you feel bad, where the adjective bad modifies the pronoun you. But when you feel badly, you are literally not good at feeling something (either physically or emotionally). See also CMOS 5.175.

Q. How should one style the title of a work in a discussion not of that work, but of its title. As an example, consider the following sentence:

The novel’s title, “Pride and Prejudice,” refers to a pair of traits seen in all of its characters.

Should the title be set in roman and within quotation marks because it is a phrase being mentioned (rather than used)? Or does the fact that it IS a title prevail, so that it should be italicized and without quotation marks? Or perhaps some tertium—or even quartum—quid? My sense is that because in that sentence its referent is not Austen’s book itself but the character flaws that recur in its plot, the italics would be inappropriate. Do I have that right?

A. You might be overthinking this. The novel’s title is Pride and Prejudice, a three-word italic phrase that names a pair of traits exhibited by many people, including the characters in that book. Chicago-style italics for book titles doesn’t prevent you from discussing what the words mean.

But if you really want to get your readers to home in on the title words as words, try something like this: “The nouns in the novel’s title, pride and prejudice, refer to a pair of traits . . .” or “The nouns in the novel’s title, ‘pride’ and ‘prejudice,’ refer to a pair of traits . . .”

For the use of italics or quotation marks to refer to words as words (either treatment is correct), see CMOS 7.66.

Q. Does CMOS have guidance for the White House’s recent changes to the names of the Gulf of Mexico and Denali?

A. Relative to matters of style, yes: Spell a generic word like gulf with an initial capital when it’s used as part of a proper name but not otherwise (“the Gulf of Mexico,” but “the gulf”; see CMOS 8.54); don’t add “Mount” before the name Denali (see 8.56); and spell out “Mount” in names like Mount McKinley rather than abbreviating it as “Mt.” (see 10.35).

Other than that, it’s easy enough to confirm that the names of those two geographic entities were officially changed (at least in the United States) to the Gulf of America and Mount McKinley, respectively, in accordance with an executive order issued on January 20, 2025, by the White House. What an author does with that information will then depend on various factors, including a publisher’s house style (if any) and considerations related to historical accuracy.

For additional guidance, see the AP Stylebook, which issues regular updates geared toward those who cover the news. In a pair of updates added on January 30, 2025, that guide says to use the original name for the gulf “while acknowledging the new name,” but, for the mountain, it says that “the Associated Press will use the new official name of Mount McKinley.” For the gulf, AP points to the long history of the older name together with the fact that the gulf shares its borders with Mexico; for the mountain, AP cites the fact that it lies entirely within the United States, which lends broader authority to that name change.

Q. With coordinate adjectives separated by a conjunction, there’s no comma: “A stable and sensible approach.” I assume it would be the same for contrasting adjectives: “A sensible yet volatile approach.” Though if you wanted to emphasize the volatility, you might set it off with commas: “A sensible, yet volatile, approach.” Does this all sound right?

A. That sounds right to us, though whenever you interrupt an adjective-plus-noun construction with an intervening phrase set off by commas, the result tends to be a little awkward. If you want to smooth things out while keeping the emphasis on volatility, try rephrasing. For example:

an approach that’s sensible yet also volatile

a sensible approach, albeit a volatile one

Or you could embrace the interruption by applying something stronger than commas:

a sensible—yet volatile—approach

a sensible (yet volatile) approach

See also CMOS 6.51.

Q. I work in curriculum. I need to be able to spell out large numbers so as to model how to read numerals correctly. I can find rules for when to hyphenate whole numbers, but I can’t find any for hyphenating decimals. Specifically, I need to know when to hyphenate the words to the right of the decimal (tenths/hundredths, etc.). Please advise. Thanks so much!

A. That’s a challenging question! Let’s start with a few numbers and how we would suggest spelling them out—on both sides of the decimal point:

1,357,201.5: one million, three hundred fifty-seven thousand, two hundred one and five tenths

1,357,201.58: one million, three hundred fifty-seven thousand, two hundred one and fifty-eight hundredths

1,357,201.580: one million, three hundred fifty-seven thousand, two hundred one and five hundred eighty thousandths

1,357,201.5803: one million, three hundred fifty-seven thousand, two hundred one and five thousand eight hundred three ten-thousandths

Note that we’ve used commas between groups of numbers to the left of the decimal point but not to the right, which reflects how the numbers are grouped (and punctuated) as digits. But we’ve treated the numbers to the left of the decimal point as a single value rather than as a series (which might require a serial comma before and).

The rules for hyphenation are the same on both sides of the decimal point (see CMOS 7.96, section 1, “numbers, spelled out”). But note that Chicago’s preference for hyphenating simple fractions doesn’t apply to five tenths in the first example above, which simply names the number in the tenths place. It does, however, apply to an ordinal fraction like ten-thousandths:

five-tenths (a simple fraction)

five tenths (the number in the tenths place; see first example above)

ten-thousandths (the ten-thousandths place; see last example above)

See also CMOS 7.96, section 1, “fractions, simple.” Finally, note that some writers add and when spelling out certain numbers that include hundred (three hundred and fifty-seven thousand; two hundred and one); Chicago omits this and (see CMOS 9.5).

Q. I am wondering how best to cite, within one chapter of a multiauthor book, other chapters from the same volume. I am accustomed to simply adding “(see chapter X)” to the text, but one author is pushing back and wants to see them in the reference list. We are using author-date style.

A. Chapters in multiauthor books are likely to be consulted separately (and are sometimes offered for individual download or sale), so listing other chapters from that same book in the reference list at the end of your own chapter wouldn’t be the worst idea. But you should still let readers know that the chapter you’re citing is in the same book.

We’d suggest adding this information to the author-date reference for that chapter in your text—for example, like this: “(Smith 2025, in this volume).” The corresponding entry in your reference list would include the book’s title (per CMOS 13.109), so a similar comment shouldn’t be needed there:

Smith, Jane. 2025. “Chapter Title.” In Title of Book, edited by Joe Anyone. Publisher details.

If you cite more than a few chapters from your book, you may want to use a shortened form for the book: “In Anyone, Title of Book.” But even if you do that, you shouldn’t need to add a separate entry in the reference list for the book as a whole, the identity of which should be obvious to anyone who is already reading something from that book. For some additional considerations, see CMOS 14.10, under “author-date.”

Q. CMOS 13.128 shows how to use author-date citations in a footnote, but what about an informational footnote like, “The history of exclusion of Chinese people in the United States has been highly researched. To begin, see . . .”? Should the parentheses around the citations be removed, as in “To begin, see Chan 1991, Lee 2003, and Kurashige 2016”? Otherwise, it might seem as though the citations are substantiating the statement, rather than being offered as suggested reading.

A. In Chicago style, the “see” in “see Chan” means that you’re referring to a work rather than a person, and the year would retain parentheses whether in the text or in a note: “To begin, see Chan (1991), Lee (2003), and Kurashige (2016).” If you’re instead referring to the author in terms of the work, the wording would need to make that clear: “See the earlier efforts by Chan (1991) to digitize the archival records.”

Parentheses for the year are omitted only when the citation is itself in parentheses, in which case semicolons rather than commas separate the sources, as in “(to begin, see Chan 1991; Lee 2003; Kurashige 2016).” But if your parenthetical reference is to an author rather than a work, the year would get square brackets: “(See the earlier efforts by Chan [1991] to digitize the archival records.)” See CMOS 13.122 and 13.124.

Q. Is it grammatically accurate to say something like, “I’m going to dress warmly”? My hunch is no, because “dress warmly” means that I’ll be smiling and emotionally warm as I’m dressing, given that “warmly” modifies the verb “dressing.” If all that is true, then what I’m unsure about is how to fix the sentence. Can you suggest any good alternatives besides writing around it like so: “I’m going to dress in warm clothing”?

A. If you say you’re going to dress warmly, that means you’re going to put on warm clothes, whereas addressing someone warmly would mean greeting that person with affection or kindness. Words often have more than one sense depending on how they’re used; according to Merriam-Webster (among other dictionaries), warmly is no exception.

Or maybe you’re thinking of the feel badly versus feel bad principle. That’s different, though, because unlike dress, the word feel can be a linking verb. Linking verbs reflect the predicate back onto the subject—as when you feel bad, where the adjective bad modifies the pronoun you. But when you feel badly, you are literally not good at feeling something (either physically or emotionally). See also CMOS 5.175.

Q. How should one style the title of a work in a discussion not of that work, but of its title. As an example, consider the following sentence:

The novel’s title, “Pride and Prejudice,” refers to a pair of traits seen in all of its characters.

Should the title be set in roman and within quotation marks because it is a phrase being mentioned (rather than used)? Or does the fact that it IS a title prevail, so that it should be italicized and without quotation marks? Or perhaps some tertium—or even quartum—quid? My sense is that because in that sentence its referent is not Austen’s book itself but the character flaws that recur in its plot, the italics would be inappropriate. Do I have that right?

A. You might be overthinking this. The novel’s title is Pride and Prejudice, a three-word italic phrase that names a pair of traits exhibited by many people, including the characters in that book. Chicago-style italics for book titles doesn’t prevent you from discussing what the words mean.

But if you really want to get your readers to home in on the title words as words, try something like this: “The nouns in the novel’s title, pride and prejudice, refer to a pair of traits . . .” or “The nouns in the novel’s title, ‘pride’ and ‘prejudice,’ refer to a pair of traits . . .”

For the use of italics or quotation marks to refer to words as words (either treatment is correct), see CMOS 7.66.

Q. Does CMOS have guidance for the White House’s recent changes to the names of the Gulf of Mexico and Denali?

A. Relative to matters of style, yes: Spell a generic word like gulf with an initial capital when it’s used as part of a proper name but not otherwise (“the Gulf of Mexico,” but “the gulf”; see CMOS 8.54); don’t add “Mount” before the name Denali (see 8.56); and spell out “Mount” in names like Mount McKinley rather than abbreviating it as “Mt.” (see 10.35).

Other than that, it’s easy enough to confirm that the names of those two geographic entities were officially changed (at least in the United States) to the Gulf of America and Mount McKinley, respectively, in accordance with an executive order issued on January 20, 2025, by the White House. What an author does with that information will then depend on various factors, including a publisher’s house style (if any) and considerations related to historical accuracy.

For additional guidance, see the AP Stylebook, which issues regular updates geared toward those who cover the news. In a pair of updates added on January 30, 2025, that guide says to use the original name for the gulf “while acknowledging the new name,” but, for the mountain, it says that “the Associated Press will use the new official name of Mount McKinley.” For the gulf, AP points to the long history of the older name together with the fact that the gulf shares its borders with Mexico; for the mountain, AP cites the fact that it lies entirely within the United States, which lends broader authority to that name change.

Q. With coordinate adjectives separated by a conjunction, there’s no comma: “A stable and sensible approach.” I assume it would be the same for contrasting adjectives: “A sensible yet volatile approach.” Though if you wanted to emphasize the volatility, you might set it off with commas: “A sensible, yet volatile, approach.” Does this all sound right?

A. That sounds right to us, though whenever you interrupt an adjective-plus-noun construction with an intervening phrase set off by commas, the result tends to be a little awkward. If you want to smooth things out while keeping the emphasis on volatility, try rephrasing. For example:

an approach that’s sensible yet also volatile

a sensible approach, albeit a volatile one

Or you could embrace the interruption by applying something stronger than commas:

a sensible—yet volatile—approach

a sensible (yet volatile) approach

See also CMOS 6.51.

Q. I work in curriculum. I need to be able to spell out large numbers so as to model how to read numerals correctly. I can find rules for when to hyphenate whole numbers, but I can’t find any for hyphenating decimals. Specifically, I need to know when to hyphenate the words to the right of the decimal (tenths/hundredths, etc.). Please advise. Thanks so much!

A. That’s a challenging question! Let’s start with a few numbers and how we would suggest spelling them out—on both sides of the decimal point:

1,357,201.5: one million, three hundred fifty-seven thousand, two hundred one and five tenths

1,357,201.58: one million, three hundred fifty-seven thousand, two hundred one and fifty-eight hundredths

1,357,201.580: one million, three hundred fifty-seven thousand, two hundred one and five hundred eighty thousandths

1,357,201.5803: one million, three hundred fifty-seven thousand, two hundred one and five thousand eight hundred three ten-thousandths

Note that we’ve used commas between groups of numbers to the left of the decimal point but not to the right, which reflects how the numbers are grouped (and punctuated) as digits. But we’ve treated the numbers to the left of the decimal point as a single value rather than as a series (which might require a serial comma before and).

The rules for hyphenation are the same on both sides of the decimal point (see CMOS 7.96, section 1, “numbers, spelled out”). But note that Chicago’s preference for hyphenating simple fractions doesn’t apply to five tenths in the first example above, which simply names the number in the tenths place. It does, however, apply to an ordinal fraction like ten-thousandths:

five-tenths (a simple fraction)

five tenths (the number in the tenths place; see first example above)

ten-thousandths (the ten-thousandths place; see last example above)

See also CMOS 7.96, section 1, “fractions, simple.” Finally, note that some writers add and when spelling out certain numbers that include hundred (three hundred and fifty-seven thousand; two hundred and one); Chicago omits this and (see CMOS 9.5).

Q. I am wondering how best to cite, within one chapter of a multiauthor book, other chapters from the same volume. I am accustomed to simply adding “(see chapter X)” to the text, but one author is pushing back and wants to see them in the reference list. We are using author-date style.

A. Chapters in multiauthor books are likely to be consulted separately (and are sometimes offered for individual download or sale), so listing other chapters from that same book in the reference list at the end of your own chapter wouldn’t be the worst idea. But you should still let readers know that the chapter you’re citing is in the same book.

We’d suggest adding this information to the author-date reference for that chapter in your text—for example, like this: “(Smith 2025, in this volume).” The corresponding entry in your reference list would include the book’s title (per CMOS 13.109), so a similar comment shouldn’t be needed there:

Smith, Jane. 2025. “Chapter Title.” In Title of Book, edited by Joe Anyone. Publisher details.

If you cite more than a few chapters from your book, you may want to use a shortened form for the book: “In Anyone, Title of Book.” But even if you do that, you shouldn’t need to add a separate entry in the reference list for the book as a whole, the identity of which should be obvious to anyone who is already reading something from that book. For some additional considerations, see CMOS 14.10, under “author-date.”

Q. CMOS 13.128 shows how to use author-date citations in a footnote, but what about an informational footnote like, “The history of exclusion of Chinese people in the United States has been highly researched. To begin, see . . .”? Should the parentheses around the citations be removed, as in “To begin, see Chan 1991, Lee 2003, and Kurashige 2016”? Otherwise, it might seem as though the citations are substantiating the statement, rather than being offered as suggested reading.

A. In Chicago style, the “see” in “see Chan” means that you’re referring to a work rather than a person, and the year would retain parentheses whether in the text or in a note: “To begin, see Chan (1991), Lee (2003), and Kurashige (2016).” If you’re instead referring to the author in terms of the work, the wording would need to make that clear: “See the earlier efforts by Chan (1991) to digitize the archival records.”

Parentheses for the year are omitted only when the citation is itself in parentheses, in which case semicolons rather than commas separate the sources, as in “(to begin, see Chan 1991; Lee 2003; Kurashige 2016).” But if your parenthetical reference is to an author rather than a work, the year would get square brackets: “(See the earlier efforts by Chan [1991] to digitize the archival records.)” See CMOS 13.122 and 13.124.