I asked ChatGPT…

Drawing of a human brain superimposed upon the circuitry of a computer chip

TL;DR: ChatGPT’s Research AI is fundamentally flawed. It misleads and hallucinates, only scratches the surface of what information is available, and ends up creating more work for the researcher than if they had just started from scratch on their own.

I set out to test ChatGPT’s Research AI to see how useful it might be in researching the history of words and phrases. There have been numerous examples in the news of late of the failure of a large language model algorithm (LLM) to accurately convey information, perhaps most notably US Health and Human Services Secretary Robert F. Kennedy, Jr. releasing a report, apparently generated at least in part by an LLM, that contained bogus source citations. My findings do not put ChatGPT’s Research AI in a good light, at least for the purposes it is being touted for.

This was a test of a large language model (LLM) for a particular purpose for which it is being touted by those selling it. LLMs may function well at other tasks, and my little test says nothing about other types of so-called artificial intelligence (AI) used for other purposes, such as image analysis tools.

I must note that what I did was not a thorough or controlled test. I was essentially just playing around with the tool. Still, what I found convinced me that constructing and conducting a thorough test would be a waste of time. When one finds fundamental errors and misinformation on one’s first “back-of the-envelope” test, that does not bode well for success in a more rigorous examination. (Which is not to say that a more thorough and rigorous test would not be welcome, just that I’m not going to bother myself.) I do think that this test is enough to conclude that one should not use ChatGPT’s Research AI or rely upon the LLM-generated summaries provided by Google and other search engines, at least until more comprehensive tests on a future, improved version show that it is reliable. I don’t, however, believe this is possible given the architecture of LLMs; the errors they produce are fundamental to and result from their design.

First, ChatGPT’s Research AI does not truly conduct “research,” in that it doesn’t create new knowledge. It is essentially a tool for literature review, finding out what others have already discovered. That is not in and of itself a bad thing—literature review is an essential function—but the label of “research” is misleading in that implies that the tool is pushing the boundaries of what is known.

I ran two separate tests of the tool. The first was to ask the origin of the word firework, the second the phrase agree to disagree. The prompts and complete LLM responses can be found below. I chose those two terms because I had written draft website entries for them, but as of the time of the test I had not published them. So I would have something to compare the LLM’s results with, but my work would not be available to the LLM and there would be no possibility of my work “contaminating” the LLM’s results.

The results of my two tests were inconsistent, with the tool performing better on one test than on the other.

On 28 May 2025, I prompted the ChatGPT Research AI to find the origin of the word firework with the following:

What is the origin of the word “firework”? Include multiple examples of early use for various senses and footnotes and bibliography in Chicago style.

(ChatGPT’s responses in full are available below.)

First, the LLM got the etymology wrong. While it correctly identified the word as a compound, it said it was “likely borrowed from similar constructs in European languages—particularly Italian fuochi artificiali (“artificial fires”) or German Feuerwerk.” This is wrong; it was most likely compounded within English.

It also said, “the earliest known usage of firework dates to 1575, and it initially referred specifically to pyrotechnic displays.” Again, this is wrong. The word dates to nearly a half century earlier, and the original sense is that of combustibles and explosives used by the military. The sense of a pyrotechnic display came later.

Then we move to the examples of use. The first, allegedly sourced from the Oxford English Dictionary (OED), was “1575 — ‘There were great fyre workes shewed upon the Thames.’” But the first citation in the OED is from 1528, and as far as I can tell the quotation the LLM gave is a hallucination, although the quotation may exist in some early-modern text that is unavailable to me using the resources of the Princeton University library. The bibliography claims the LLM accessed the OED on 28 May 2025, the day I asked the question. Clearly, it did not.

The second example is allegedly from George Puttenham’s The Arte of English Poesie. The citation is dated 1691, although Puttenham’s book was published two years earlier. The LLM’s dating is also internally inconsistent: while the text gives the date as 1691, both the footnote and bibliography give the correct date for the work, 1689. And again, the LLM hallucinated the quotation; Puttenham’s book doesn’t use the word fireworks.

The next example given is in a military context. The author, Henry Hexham, did indeed write about military affairs in the period, but as far as I can tell the book, a 1625 text titled A Treatise of the Art of Warre, does not exist.

The last example of use is in the figurative sense, allegedly taken from John Milton’s 1671 Paradise Regained. At least this time the book is real; the quotation, however, is not.

Finally, the LLM notes, “By the 18th century, ‘fireworks’ had also come to denote a spectacle or a display of emotion, often intense or dramatic.” Again this is incorrect. This figurative sense was in place at the start of the seventeenth century.

The second test was to find the origin of the phrase agree to disagree. The LLM did much better at this one. There were no hallucinations, and it did not fall for the common belief that the phrase was coined by theologian John Wesley. The information it provided was essentially correct; the only “errors” I found was giving a first citation of 1608, when the earliest I have found is 1601, and the quotation from Wycherley does not cite the earliest edition of the poem. These are not disqualifying.

The chief problem with this second response is it did not format the notes or bibliography in Chicago style, as requested. Page numbers and other critical information were missing from the scholarly apparatus, making it difficult to find the sources being referenced. This sounds like a quibble, but it is significant. The purpose of source citations is to allow readers to locate the original information; if page numbers are not provided, this task becomes difficult, if not all but impossible. Also, formatting source citations to conform with a particular published style is something that LLMs should perform nearly flawlessly but that this current iteration of ChatGPT's Research AI cannot accomplish.

A lesser, but highly revealing, problem is the type of sources cited. It seems that all of the primary source citations were gleaned via two articles, a blog post and a newspaper article. While in this particular case both of these were well researched, that is not always the case with blogs and newspapers. They should not be the go-to secondary sources for serious research, used only upon careful assessment of their quality. In this instance the LLM was fortunate in stumbling upon two good ones. I say fortunate, because the hallucinations in the first test make it clear that the LLM is incapable of assessing information quality.

The question arises is why did the LLM fail so miserably on the one task, yet do a decent job on the other? While LLM is a black box and the answer cannot be known for certain, I think the answer lies in the two terms chosen. The term firework has little online commentary about its origin, while there is extensive commentary about the origin of agree to disagree (most of it centered on the belief that Wesley coined it). And, indeed, all the information and quotations provided in this second response can be found in the two secondary sources that the LLM cited. So when it has information that is succinctly and correctly stated in a readily available source (e.g., a blog post or Wikipedia), the LLM does a reasonable job. But when it needs to assemble a response on its own, it falls into hallucination and error.

From this brief test, it is clear that ChatGPT’s Research AI is worse than useless in the tasks it is being touted for. It is actively misleading. This should not be a surprise. Large language models (LLMs) are essentially predictive text engines, determining what is the most statistically likely word to follow. They are not “intelligent” in any sense of that word. They have no knowledge of the real world or what is true or false, fact or fiction. As a result, I do not believe it is possible to create an LLM that can perform this function adequately. Not only are the answers it produces not to be trusted as correct, those answers are not even internally consistent within the same response, as the different dates given for Puttenham’s work show.

Discuss this post

Image credit: Unknown creator, 2018. Wikimedia Commons. Public domain image.

 The prompts and responses follow:

 

First Prompt to ChatGPT’s Research AI:

What is the origin of the word "firework"? Include multiple examples of early use for various senses and footnotes and bibliography in Chicago style.

ChatGPT’s response:

The word "firework" has an intriguing etymology that traces back to the early modern English period, and its development reflects both the literal and figurative senses in which it has been used over time. Here's a detailed breakdown of its origin, historical usage, and references in Chicago style.

Origin and Etymology

The English word “firework” is a compound of “fire” and “work,” following the common practice in Germanic and Romance languages of forming compounds to describe man-made contrivances involving fire. The term appears in English in the late 16th century, likely borrowed from similar constructs in European languages—particularly Italian fuochi artificiali ("artificial fires") or German Feuerwerk.

According to the Oxford English Dictionary (OED), the earliest known usage of firework dates to 1575, and it initially referred specifically to pyrotechnic displays.

Examples of Early Use

1. Literal Sense: Explosive Display

  • 1575 – “There were great fyre workes shewed upon the Thames.”1
    This is among the earliest known usages, documenting a pyrotechnic celebration held for Queen Elizabeth I. The spelling reflects the orthographic conventions of the period.

  • 1591 – George Puttenham, in The Arte of English Poesie, refers to “artificiall fires and fireworks,” demonstrating that the term had entered broader descriptive vocabulary by the end of the 16th century.2

2. Military and Technical Context

  • 1625 – In A Treatise of the Art of Warre by Henry Hexham, we find mention of “diverse sorts of fireworks used in assault.”3
    Here, the term applies to military pyrotechnics, such as incendiary devices and signal flares.

3. Figurative Sense

  • 1671 – John Milton’s Paradise Regained includes a metaphorical use: “Flames of zeal... not fireworks for the eyes.”4
    This marks one of the earliest known figurative uses, contrasting superficial spectacle with spiritual intensity.

Development of Senses

By the 18th century, "fireworks" had also come to denote a spectacle or a display of emotion, often intense or dramatic. This figurative usage still persists today, as in “There were fireworks during the debate.”

Conclusion

The term firework has evolved from its initial technical and celebratory meanings to encompass broader metaphorical connotations. Its roots lie in European traditions of pyrotechnic display, and its usage in English reflects both cultural practices and linguistic borrowings.

Footnotes

Bibliography

  • Hexham, Henry. A Treatise of the Art of Warre. London: M. Flesher, 1625.

  • Milton, John. Paradise Regained. In The Complete Poetry and Essential Prose of John Milton, edited by William Kerrigan, John Rumrich, and Stephen Fallon, 543. New York: Modern Library, 2007.

  • Oxford English Dictionary. “Firework.” Accessed May 28, 2025. https://www.oed.com.

  • Puttenham, George. The Arte of English Poesie. London: Richard Field, 1589.

Would you like this formatted as a PDF or added to a document?

Footnotes

  1. Oxford English Dictionary, s.v. “firework,” accessed May 28, 2025, https://www.oed.com.

  2. George Puttenham, The Arte of English Poesie (London: Richard Field, 1589), 135.

  3. Henry Hexham, A Treatise of the Art of Warre (London: M. Flesher, 1625), 74.

  4. John Milton, Paradise Regained, in The Complete Poetry and Essential Prose of John Milton, ed. William Kerrigan, John Rumrich, and Stephen Fallon (New York: Modern Library, 2007), 543.

 

 

Second Prompt to ChatGPT’s Research AI:

What is the origin of the phrase “agree to disagree”? Include multiple examples of early use for various senses and footnotes and bibliography in Chicago style.

ChatGPT’s response:

Origin and Early Usage of “Agree to Disagree”

Historical Development

  • 1608 – James Anderton (alias John Brereley)

    • In The Protestants Apologie for the Roman Church, Anderton writes:

“And as our learned adversaries do thus agree to disagree in their owne translations, mutually condemning (as before) each other...”

    • This usage lacks the modern connotation of mutual tolerance and instead highlights conflicting viewpoints among Protestant scholars.
      https://wjdw.nl/2019/04/12/was-john-wesley-the-first-to-put-the-phrase-agree-to-disagree-in-print/?utm_source=chatgpt.com

  • 1704 – John Piggott

    • In his sermon On Union and Peace, Piggott states:

“And now why should we not agree to differ, without either enmity or scorn?”

    • This reflects an early sentiment of amicable disagreement.
      https://en.m.wikipedia.org/wiki/Agree_to_disagree?utm_source=chatgpt.com

  • 1706 – William Wycherley

    • In the poem An Epithalamium on the Marriage of Two very Ill Natur’d Blacks, Wycherley writes:

“Who, like Black Fiends, agree to disagree, | Each other’s Torment, out of Love to be.”

    • This usage suggests a mutual, albeit contentious, relationship.
      https://wjdw.nl/2019/04/12/was-john-wesley-the-first-to-put-the-phrase-agree-to-disagree-in-print/?utm_source=chatgpt.com

  • 1750 – George Whitefield

    • In a letter dated June 29, 1750, Whitefield remarks:

“After all, those who will live in peace must agree to disagree in many things with their fellow-labourers, and not let little things part or disunite them.”

    • This reflects the modern sense of maintaining harmony despite differences.
      https://wjdw.nl/2019/04/12/was-john-wesley-the-first-to-put-the-phrase-agree-to-disagree-in-print/?utm_source=chatgpt.com

  • 1770 – John Wesley

    • In his sermon On the Death of Rev. Mr. George Whitefield, Wesley states:

“There are many doctrines of a less essential nature ... In these we may think and let think; we may 'agree to disagree.' But, meantime, let us hold fast the essentials...”

    • Wesley attributes the phrase to Whitefield, indicating its prior usage.
      https://www.southernstandard.com/opinions/where-did-that-come-from-agree-to-disagree/?utm_source=chatgpt.com
      https://en.wikipedia.org/wiki/Agree_to_disagree?utm_source=chatgpt.com

Footnotes

  1. James Anderton (as John Brereley), The Protestants Apologie for the Roman Church, 1608.

  2. John Piggott, Eleven Sermons, 1714, p. 290.

  3. William Wycherley, Miscellany Poems, 1706, p. 432.

  4. George Whitefield, Letter to Mr. B., June 29, 1750.

  5. John Wesley, A Sermon on the Death of the Rev. Mr. George Whitefield, 1770.
    https://wjdw.nl/2019/04/12/was-john-wesley-the-first-to-put-the-phrase-agree-to-disagree-in-print/?utm_source=chatgpt.com
    https://en.wikipedia.org/wiki/Agree_to_disagree?utm_source=chatgpt.com
    https://www.southernstandard.com/opinions/where-did-that-come-from-agree-to-disagree/?utm_source=chatgpt.com

Bibliography (Chicago Style)

  • Anderton, James (as John Brereley). The Protestants Apologie for the Roman Church. 1608.

  • Piggott, John. Eleven Sermons. London: 1714.

  • Wycherley, William. Miscellany Poems. London: Jeffery Wale, 1706.

  • Whitefield, George. Letter to Mr. B., June 29, 1750.

  • Wesley, John. A Sermon on the Death of the Rev. Mr. George Whitefield. London: J. and W. Oliver, 1770.

Further Exploration

  • Investigate the evolution of the phrase's meaning over time.

  • Compare with similar expressions like "agree to differ."

  • Examine the phrase's usage in contemporary discourse.

antisemitism vs. anti-Semitism

18 March 2025

The copyeditor in me noticed that the Donald Trump’s executive order of 29 January 2025 titled Additional Measures to Combat Anti-Semitism uses the hyphenated and capitalized form of that word instead of now usually preferred forms antisemitism and antisemitic. The change in preferred spelling is both an example of a rapidly changing usage and of the sloppiness and inattention to detail, and perhaps even malicious intent, that is characteristic of the Trump administration.

Ten years ago, the form anti-Semitism was the overwhelmingly preferred spelling; the Corpus of Contemporary American English, with data up to the year 2012, records 3,108 hits for that spelling compared to only 618 for antisemitism. But the preferred spelling has rapidly changed over the past decade. The News on the Web (NOW) corpus records 3,062 hits for anti-Semitism in the year 2024, compared to 18,777 for antisemitism. The ratio of 5: or 6:1 remains steady, only it has flipped in favor of the antisemitism spelling.

This shift can also be seen by comparing the U.S. Department of State’s current statement on Defining Antisemitism with its statement on Defining Anti-Semitism issued in 2010. (The State Department’s website does not give a date for the current statement, but the department’s shift in spelling seems to have occurred during the Biden administration.)

As to the origin of the term, the French adjective antisémitique, in the sense of prejudice toward Jews, appears by 1868, and the German noun Antisemitismus was in use by 1876, popularized, if not coined, by journalist and antisemite Wilhelm Marr. Both adjective and noun, in hyphenated form, had entered widespread English usage by 1879.

The shift in spelling, dropping the hyphen and capital letter, began in earnest in April 2015 when the International Holocaust Remembrance Alliance (IHRA) announced a preference for the antisemitism spelling, claiming that hyphen and capitalization of Semitism “not only legitimizes a form of pseudo-scientific racial classification that was thoroughly discredited by association with Nazi ideology, but also divides the term, stripping it from its meaning of opposition and hatred toward Jews.” The Anti-Defamation League (ADL) followed suit in 2021, as did other organizations and editors.

But dictionaries have yet to catch up with this shift in spelling. Dictionaries tend to be slow, both because their editorial bandwidth is limited and because they generally want to focus on lasting usages and not respond to every shift in fashion. Although given the sensitive nature of the term, perhaps by this point they should move antisemitism up on the list priorities to edit. The Oxford English Dictionary (OED), from 2019, only makes mention of the antisemitism spelling in its listing of forms of the word; all its usage citations are of anti-Semitism. Merriam-Webster’s only mention of the antisemitism spelling is a note saying it is used “less commonly.” And the 2022 fifth edition of the American Heritage Dictionary makes no mention of antisemitism spelling at all.

The Chicago Manual of Style is more up to date. For some time, that style guide’s preference has been for a “spare hyphenation style” that as a general rule does not use hyphens between prefixes and roots; this general rule is unchanged from at least the 2003 fifteenth edition. (I did not look further back.) However, the 2024 18th edition of CMOS’s Hyphenation Guide includes antisemitism as an example of this spare hyphenation style, where previous editions did not give this specific example.

As to why the Trump administration deployed the anti-Semitism spelling, the Times of Israel (14 March 2025) reports that the Trump administration has not responded to inquiries about the spelling. One might think it is a knee-jerk reaction to the “liberal Biden administration’s” use of antisemitism, but conservative media outlets like Fox News and Breitbart also use that spelling, as does virtually all of the Israeli press. It is possible the Trump White House simply consulted dictionaries as to the correct spelling. But while this might be a legitimate excuse for an ordinary writer, one would hope that when crafting a policy on antisemitism the White House would be consulting experts and be aware of the shift in spelling. About the only explanations that makes sense are that it is yet another example of sloppy and poorly worded and executed policies that are coming out of the current White House or that they actually prefer the anti-Semitism spelling.

Does the spelling matter? On one level, it doesn’t. Spelling isn’t going to alter anyone’s views toward Jews. If the anti-Semitism spelling contributes toward hatred of Jews, that contribution is marginal at best. But on another level, it does matter. When one sees someone use the anti-Semitism spelling in 2025, one can rightly conclude that, at best, they are unaware of the difference. And when one sees the White House using it, one can only conclude that they aren’t serious about combatting antisemitism or, worse, that they are antisemitic themselves.

Discuss this post

Sources:

American Heritage Dictionary, fifth edition, 2022, s.v. anti-Semitism, n., anti-Semite, n. Accessed 18 March 2025.

Anti-Defamation League (ADL). Spelling of antisemitism vs. anti-Semitism, n.d. Accessed 18 March 2025.

Chicago Manual of Style, 18th edition, 2024, 7.96: Hyphenation Guide, 17th edition, 2017, 7.89: Hyphenation Guide, and 15th edition, 2003, 7.90: Hyphenation Guide (Archive.org). Accessed 18 March 2025.

Davies, Mark. Corpus of Contemporary American English (COCA). Accessed 18 March 2025.

———. News on the Web Corpus (NOW). Accessed 18 March 2025

Elia-Shalev, Asaf. “Breaking with Consensus, Trump Makes ‘anti-Semitism’ Hyphenated Again.” Times of Israel, 14 March 2025. Accessed 18 March 2025.

International Holocaust Remembrance Alliance (IHRA). Spelling of antisemitism, April 2015. Accessed 18 March 2025.

Lebovic, Matt. “What’s in a Hyphen? Why Writing anti-Semitism with a Dash Distorts Its Meaning.” Times of Israel, 23 August 2018. Accessed 18 March 2025.

Merriam-Webster.com, anti-Semitism, n., and anti-Semitic, adj. Accessed 18 March 2025.

Oxford English Dictionary, third edition, December 2019, s.v. anti-Semitism, n., anti-Semitic, adj. Accessed 18 March 2025.

Trump, Donald J. Additional Measures to Combat Anti-Semitism. The White House, 29 January 2025. Accessed 18 March 2025.

U.S. Department of State. Defining Anti-Semitism, 8 June 2010. Accessed 18 March 2025.

———. Defining Antisemitism, n.d. Accessed 18 March 2025.

ADS 2024 Word of the Year (WOTY)

A woman and two men at the front of a conference center meeting room

Chairs of the 2024 ADS WOTY nominating session, l to r, Kelly Elizabeth Wright, Charles Carson, and Ben Zimmer

The American Dialect Society has selected rawdog as its 2024 Word of the Year (WOTY 2024). Rawdog is an excellent choice for a number of reasons. The word dates to at least 2002—to be considered, words need only to be newly prominent, not newly coined, in the year in question—with an original sense of to have unprotected sex. In recent years, rawdog has semantically broadened, coming to mean to engage in any activity recklessly or without protection, such as braving Covid without a mask or vaccine or cooking an unfamiliar meal without a recipe. One can rawdog a long aircraft flight by boarding without reading material or a movie. In fact, there is even a game where users compete as to who can rawdog the longest on a flight that uses an app on the player’s phone to measure eye movement, penalizing them if they don’t stare straight ahead.

Many organizations and individuals (including me) promote a word or words or the year, but the ADS is the oldest, having done so for some thirty-five years. The ADS is a 135-year-old professional organization made up of linguists, lexicographers, and others that studies the languages of North America. It has published the journal American Speech for the last hundred years.

Each year in early January, the organization meets, in recent years in conjunction with the larger Linguistic Society of America. The primary purpose of the meeting is an academic conference where members present papers and further the scholarly aims of the society. In contrast, the WOTY selection is a fun diversion and an opportunity to raise public awareness about language change. In short, while the selection itself is unserious (a word that itself was one of this year’s nominees), the process can be enlightening.

I’ve been following and writing about the ADS WOTY for over two decades, and on occasion I’ve participated in the proceedings, as I did this year. (I usually show up if I’m also giving a paper at the conference, as I did this year.) You can read ADS press release which provides the list of winners, nominees, and vote count by clicking this link. But here I’m going to discuss my impressions of the process and the selections.

The selection occurs in two steps. The first is a nominating session, held the day before the final selection where nominations for words in the subcategories are made. Some subcategories, like Most Useful and Political Word of the Year are perennial, and ad hoc subcategories can be proposed if appropriate for that particular year. I proposed a category that seemed fitting for several of the words this year, Most Fun While It Lasted, although someone else came up with that most apropos wording for the title. In my opinion, this is the more fun and interesting session. It’s smaller (there were about fifty people there), and as a result the discussion is livelier, more in depth, and a bit more scholarly inclined (but still fun and unserious; to give a sense of the tone, co-chair Kelly Elizabeth Wright was dubbed the nominatrix). More importantly, terms used by more marginal and underrepresented groups are more likely to be raised and discussed in depth in this session.

The final selection is made the next night. That session is much larger; some 350 were in attendance this year. Nominees in the subcategories are voted on, and nominees are made for the WOTY itself and then voted upon. If no nominee gets fifty percent of the vote on the first ballot, a runoff between the top two vote-getters is held. Because the crowd is much larger and there are time constraints (another unrelated conference session uses the big room immediately after), the discussion is more constrained. It’s still fun, though. There is a tradition of running satirical commentary in the visual presentation of the nominees, this year by Jessica Grieser, filling in for Grant Barrett who usually provides the snark. (As an example, when co-chair Ben Zimmer’s son stood up to comment on the combining form -maxxing, Jessica typed Zimmermaxxing into the display.)

Now on to what I think of the nominees and final selections.

For the big one, the overall WOTY, rawdog won in a runoff against sanewashing. Despite requiring a runoff, the choice was not that close. Rawdog nearly got fifty percent on the first ballot, with the other nominees splitting the rest of the vote. I think it is an excellent choice. It is newly prominent, encapsulates a trending social phenomenon, and is linguistically interesting.

Lock in took top honors in the Most Useful category, another excellent choice. To lock in is to achieve a state of deep focus and concentration, and one can see it being used for many years hence. Other nominees included cooked, to be exhausted or in serious trouble. While it is currently in newly prominent slang use, this sense has been in common and continuous use since the mid nineteenth century, calling into question its qualification. Crash out is a noun and verb referring to having reached one’s limit or as a result reacting in an irrational or overly emotional manner. Both cooked and crash out were also nominated for the overall WOTY. The final nominee in this category is eat, in the sense of accomplishing something extremely well, with a superlative of devour, and a past tense of 4+4 (ate), displaying linguistic inventiveness. The nominees were all good, but I agree that lock in best fits the spirit of the category.

Unserious won the Most Likely to Succeed category. While the word dates to the seventeenth century, its use as a putdown is relatively new. It is a reasonable choice, but I don’t think it was the best. That was NIL, a legal initialism arising out the court cases requiring the NCAA to compensate college athletes for use of their name, image, or likeness. Not only is the term new, but it will undoubtedly be used in legal discourse for ages to come. The other nominees were less appropriate for the category. Aura, a charismatic presence, is an already well-established word that has recently gained increased currency in youth slang. Girlypop, a fun, trusted, and distinctly feminine female friend (also an adjective describing one) was a new one to me, and while it may last, its chances are distinctly less than either NIL or unserious. Finally, there was tariffied, that is being afraid or worried over the economic consequences of Donald Trump’s proposed tariffs on imported goods. While it is a clever coinage, there is no way it will outlast the incoming administration (and probably not even that long), making it distinctly inappropriate for this category.

ADS’s Political WOTY is Luigi, a reference to Luigi Mangione, who in December assassinated UnitedHealthcare CEO Brian Thompson. While it is a productive root, acting as noun and verb and in numerous compounds, it suffers from the end-of-year bias that is present in most WOTY discussions. I was pulling for broligarchy , which I thought had more staying power throughout the year and has a better chance of remaining in use. Sanewashing and weird were also nominees that were deserving of winning. Sanewashing was also a nominee for overall WOTY. Honorable mention goes to bleach blonde bad built butch body, a retort delivered by Rep. Jasmine Crockett (D-Texas) to Rep. Marjorie Taylor Greene (R-Georgia) in a House of Representatives committee meeting after Greene insulted her appearance. While the exact term is very much of a particular moment, it is representative of a type of insult discourse that is common among Black women, a group that is often left out of WOTY consideration. Burrito taxi, a mocking of complaints about inflation of grocery prices by people who order meal delivery to their homes, and lib out, the unrealistic hopes of Democratic victory in the year’s elections, were also nominated.

Brainrot, mental deterioration from consuming too much social media or that media itself, took honors for Digital WOTY. It’s a good choice, but I preferred AI slop (or just slop) referring to computer-generated content, especially the flood of such content that fills Google search results. It’s new this year, and we’re going to be contending with AI slop for many years to come. Xit/Xodus was another reasonable choice, referring to users abandoning Twitter/X en masse, but that’s another term of the moment that will not have longevity. Cope, a nouning of the verb coined in response to the prospects of the deteriorating of American politics as nominated, as was tradwife, a social media phenomenon, and an ironic one at that as being a social media influencer is hardly traditional.

The Informal WOTY was rawdog, winning handily, although there was a strong showing by yap, referring to excessive or overly enthusiastic speech, used both negatively and positively. While the negative use is hardly newly prominent, the positive use is, and in 2024 it was very common among youth, making it a reasonable nominee. Yap was also a nominee for overall WOTY. Cooked was also a nominee. The other three, mewing, mog, and W, were all new to me and deservedly trailed in the voting.

Most Creative honors deservedly went to the snowclone the X I Xed, where one invents an irregular past tense of a regular verb, as in the gasp I gusped or the scream I scrempt. The combining form -maxxing took a distant second. I have a certain fondness for the nominee in da clerb, we all fam, a quotation from the television sitcom Broad City, which became a TikTok trend in 2024. I like it, but it’s not as apt a choice as the X I Xed. And broligarchy was also in the mix but didn’t get much traction in this category’s votes.

Finally there was the ad hoc category of Most Fun While It Lasted, which I proposed mainly because of brat, which took the category handily. Demure, a new sense referring to modest and reserved appearance, hawk tuah, an echoic term for spitting, especially before performing oral sex, that was inspired by a viral video, and hold space, the nonjudgmental creation of a safe space were nominees that didn’t stand a chance against brat, which was also a nominee for overall WOTY.

That was this year’s crop of WOTY winners and nominees. Overall, it was a pretty good grouping of terms of significance in the past year. Of course one can disagree with any of the choices or my opinions about them; there’s nothing scientific or academically rigorous about the process. But it is an entertaining exercise that makes one think about the events of the past year and the language we used to refer to them.

Photo credit: Dave Wilton, 2025. CC BY-NC-SA 4.0