.svg){kind=logo}
Consultations that should lead to an updating of the Wikimedia Foundation's Terms of Use will begin as early as this Tuesday, February 21 according to WMF Legal. The discussions will take place on Meta-Wiki.
The updates are necessary in order to:
Other possible changes include strengthening enforcement of the requirement that paid editors must declare their employers, clients, and affiliations. – S
Wikimedia Foundation Board Member Shani Evenstein announced the results of the vote on the Wikimedia-l mailing list on 13 February 2023:
Today the results of the Universal Code of Conduct Enforcement Guidelines vote were tallied. We are pleased to report the results show that the Enforcement Guidelines are strongly supported by the community, with 76% of participants voting in support of the Enforcement Guidelines.
3,097 voters from 146 Wikimedia communities participated. Statistics for the vote are available. A more detailed summary of comments submitted during the vote will be published soon.
Next, the results and comments collected during this vote will be submitted to the Board of Trustees for their review. It is expected that the Board of Trustees review process will complete in March 2023, at which time another update will be published. – AK
The Steward elections are underway. New candidates for Stewardship are:
The Steward confirmations – an annual performance evaluation by the community that determines whether or not existing Stewards will retain their status for another year – are also currently underway.
Voting for the election and confirmation processes will remain open until 26 February 2023, 21:00 (UTC). – AK
.jpg)
Now you see it, now you don't – Wikipedia had hardly been blocked by Pakistan before it was unblocked.
Shehbaz Sharif, the Prime Minister of Pakistan, stepped in and convened a committee composed of the Minister for Law and Justice, the Minister for Economic Affairs and Political Affairs and the Minister for Information and Broadcasting to examine the matter.
The committee took the view that –
Wikipedia was a useful site/portal which supported dissemination of knowledge and information for the general public, students and the academia. Blocking the site in its entirety was not a suitable measure to restrict access to some objectionable contents/sacrilegious matter on it. The unintended consequences of this blanket ban, therefore, outweigh its benefits.
The government subsequently barred the Pakistan Telecommunication Authority (PTA) from blocking any website without first consulting the Ministry of Information Technology and Telecommunication.
Wikimedia Foundation General Counsel Stephen LaPorte said on the Wikimedia-l mailing list:
We received news yesterday that the Pakistan Telecommunications Agency was directed to restore access to Wikimedia projects, including Wikipedia, in Pakistan. Our internal traffic reports confirm that the block has been lifted and we've updated our public statement.
We're happy that the people of Pakistan can continue to use Wikipedia to access knowledge and share their experiences and culture with the world. These situations are a reminder of the importance of the work of our movement and the vital role our communities play in building the largest collection of open knowledge in history. It also underscores the need to protect people's right to access free knowledge and participate in contributing to its growth globally. Thank you for your support. We'll continue to keep you updated if there are any new developments.
For the media coverage of this event, see this issue's in the media.
a sense of what is real and what is fake
Last issue, we reported on AI-generated articles on Wikipedia. It was a bit of fun. Find the AI-generated article! The impostor is sus!
If only it remained that way: English Wikipedia editor Rory Jaffe (rsjaffe) has found a number of them, including Draft:Cow Farts – not actual bull shit, but pretty close. Here's what he says about his discovery technique.
I've been looking for "tells" before testing [with a classifier tool that can detect AI generated text with some accuracy]. The text is more "lifeless" than human text typically is, tends to have uniform length sentences, and may have a paragraph at the end that is a summary paragraph. The text is also unlikely to have in-line references. This doesn't catch all of them but tends to be a high-likelihood way of finding them. Some of these AI-generated articles also have AI-generated references. The references are almost always fake: the AI confabulates reasonable-sounding references!
Articles or drafts tagged by Jaffe and reviewed by The Signpost were created as early as 17 December 2022 (Draft:Brisbane Lord Mayor YAC). The topics tagged by Jaffe and others range from the whimsical and neologism-ic (Draft:Twinkanic Awareness, Draft:Sharks should be saved from humans) to the plausibly- and obviously-promotional, and appear to be created by many editors, including single-purpose accounts that may be using them for promotion. Take Draft:Dachshund harness, "an essential accessory for owners of this unique breed of dog", which has a list of references at the end related to shopping for such a device. Given affiliate marketing exists, this could be promotional. Or it could be purely accidental. We don't know. Some of the rest may be deleted by the time you read this – a few examples are retained permanently at User:JPxG/LLM dungeon.
The Signpost asked Jaffe "Do you have a personal reaction to the quality of the AI generated articles? Briefly, are you for or against this method of creation?" He told us this:
Strongly against. These language generators are good at stringing together reasonable-sounding text, but:
1. Don't rely solely on what Wikipedia recognizes as reliable sources.
2. Don't have a sense of what is real and what is fake.
3. Will fabricate information to fill in gaps.
4. Cannot identify where any specific bit of "information" came from.
So the text can fail WP:RS and WP:V, yet may look very convincing.
However, they're good at helping to break "writer's block", by giving an example of how to write something. So I see having some text generated by ChatGPT would be helpful as a writing prompt, but without using any of the generated text directly—just looking at it and then writing a well-researched article similar to the prompt.
More on Jaffe's experience and conclusions on this topic can be found at the Essay in this issue.
We asked ChatGPT for a commentary as well. It said:
It's interesting to see that people are now using AI to generate articles on Wikipedia, but it's also concerning as this could lead to a proliferation of inaccurate or fake information on the platform. It's good to see that editors like Rory Jaffe are using techniques to identify AI-generated text, but it's clear that the AI-generated articles are becoming more sophisticated in their structure and references, making it harder to detect them.
It's important for Wikipedia to maintain its high standards of accuracy and reliability, so it's crucial that the platform continues to monitor and regulate the use of AI-generated content. While AI can be a valuable tool for assisting with research and writing, it should never be a substitute for human expertise and critical thinking.
Wikimedia Enterprise has published its first detailed financial report, complete with a summary of product updates.
Revenue in the 2022 calendar year (from subscription and professional services) totaled $3.12 million, vs. expenses of $3.18 million ($1.06 million in cost of services and $2.12 million in operating expenses), for a net loss of $60,000.
The Enterprise team points out that the present report for the 2022 calendar year should be considered a "beta" edition. The Wikimedia Foundation normally operates on a financial year starting in July and finishing the following June. But as January 1, 2022 marked the official start of commercial operation of the Enterprise project, this first report covers the 2022 calendar year. For future financial reports the Enterprise team intends to align with the normal financial reporting schedule of the rest of the Wikimedia Foundation. The next report will be published in late 2023.
The report adds that:
As the LLC is wholly owned by the Wikimedia Foundation, all of the financial information presented here will also be included within the Wikimedia Foundation's audited financial statements and will be in the next Wikimedia Foundation "Form 990" filing as it relates to fiscal year 2021–2022, and future years.
The Enterprise team says it is very happy with its first year in business and looks forward to growth and profitability this year:
In 2023, our second year of operations, with the addition of new customers and also new features, both revenue and expenses are expected to increase – but revenue growth is expected to outpace expenses. By comparison to other startup commercial API projects, to reach this stage within one year of operations is extremely rapid progress. The governance of these and all other commercial customer relationships is consistent with how the Wikimedia Foundation treats large corporate donations.
No information has been released on how many paying and non-paying customers Wikimedia Enterprise has at the moment. Corresponding inquiries on Meta-Wiki have been answered as follows:
As stated in the original press release, Google and the Internet Archive are indeed the first to receive paid and free access (respectively) but we have not publicized the subsequent customers (paid or free) who have signed-up to the service. ... Maintaining a public and comprehensive list of paying and free/trial customers would look like advertising/promotion of those customers, and also introduce a new privacy (and potentially security) problem: i.e. in the same way that it would be inappropriate to make a public list of "all people who have used the Wikidata Query Service this month" (for example) – it goes against our privacy culture. Nonetheless, we do intend to be making "use case" blog posts – which will describe how some users (either general categories or individual cases with their permission) are benefiting from the service in the real-world.
The Enterprise API features are designed with large commercial reusers in mind – primarily search engines and voice assistants, although education (question-and-answer modules), finance and the fast-growing AI sector represent additional market opportunities the team may explore.
But other kinds of reusers, including individual volunteer Wikimedians, can also benefit. There are several access methods to the datasets available at no cost/no registration, including a free Wikimedia Enterprise account via the project's homepage. Ongoing updates for the community can be found on the project's MediaWiki page.
The publication of the financial report was followed by a public Zoom meeting on 10 February, a recording of which is available. Click the picture on the right or go to the Wikimedia Enterprise talk page on Meta-Wiki, which also includes a list of questions discussed during the meeting and their approximate timecodes. The file description in Commons even includes an automated transcript. – AK
In response to multiple inquiries, the Wikimedia Foundation has posted a breakdown of how and when Tides Advocacy spent the $4.223 million Annual Plan Grant portion of the $8.723 million the organisation received from the WMF in the 2019–2020 financial year. – AK
.jpg)
An essay published on 9 February 2023 in The Journal of Holocaust Research and reported on by Haaretz and Polish daily Wyborcza, as well as San Diego Jewish World and Ynet, alleges that Wikipedia engages in "intentional distortion of the history of the Holocaust". The abstract of the essay, written by Jan Grabowski of the Department of History at the University of Ottawa and Shira Klein of the Department of History at Chapman University in Orange, California, says:
This essay uncovers the systematic, intentional distortion of Holocaust history on the English-language Wikipedia, the world’s largest encyclopedia. In the last decade, a group of committed Wikipedia editors have been promoting a skewed version of history on Wikipedia, one touted by right-wing Polish nationalists, which whitewashes the role of Polish society in the Holocaust and bolsters stereotypes about Jews. Due to this group's zealous handiwork, Wikipedia's articles on the Holocaust in Poland minimize Polish antisemitism, exaggerate the Poles' role in saving Jews, insinuate that most Jews supported Communism and conspired with Communists to betray Poles (Żydokomuna or Judeo–Bolshevism), blame Jews for their own persecution, and inflate Jewish collaboration with the Nazis. To explain how distortionist editors have succeeded in imposing this narrative, despite the efforts of opposing editors to correct it, we employ an innovative methodology. We examine 25 public-facing Wikipedia articles and nearly 300 of Wikipedia’s back pages, including talk pages, noticeboards, and arbitration cases. We complement these with interviews of editors in the field and statistical data gleaned through Wikipedia's tool suites. This essay contributes to the study of Holocaust memory, revealing the digital mechanisms by which ideological zeal, prejudice, and bias trump reason and historical accuracy. More broadly, we break new ground in the field of the digital humanities, modelling an in-depth examination of how Wikipedia editors negotiate and manufacture information for the rest of the world to consume.
On 13 February 2023, Wikipedia's primary disciplinary body, the Arbitration Committee, took the unusual step of initiating a case request sua sponte in response to the essay, "invoking its jurisdiction over all matters previously heard and exercising its authority to revisit any proceeding at any time at its sole discretion." The topic area – including many of the edits and behaviours discussed by Grabowski and Klein – has been the subject of multiple arbitration proceedings before, from the 2009 Eastern European mailing list case to the 2019 Antisemitism in Poland case.
On 15 February 2023, Wyborcza (the Polish newspaper that carried Grabowski and Klein's summary of their essay) published a rebuttal by Piotr Konieczny of the Department of Media and Social Informatics at Hanyang University, one of the Wikipedians (User:Piotrus) named by Grabowski and Klein. Piotr said the essay contained many assertions of fact that were not borne out by edit histories recorded on Wikipedia, as well as instances of selective quoting. For those who don't subscribe to Wyborcza – the paper is paywalled – the text of the rebuttal is available here. A longer, English-language response by Piotr raising some of the same issues is here. Volunteer Marek, another editor named in the essay, has also published a multi-part response in English on his Substack.
Watch out for an independent review of the paper in the upcoming issue of the Signpost's monthly "Recent research" section. In the meantime, see also previous Signpost coverage of similar complaints raised in 2019. – AK
This is the premise of an article series investigative journalist Russ Baker kicked off on 6 February 2023 with a piece on his whowhatwhy.org website.
Baker is a veteran reporter who has written for top publications like The New Yorker and The Washington Post. He has tussled with the Church of Scientology. In 2005, he won the Deadline Club award for his exclusive reporting on George W. Bush's military record. Baker was among the first to cast doubt on Colin Powell's now-infamous presentation on Iraq at the United Nations – at the time a very unpopular stance – and among the first to make Americans aware of the impending genocide in Rwanda. But presently, he is concerned about Wikipedia's biographies.
Baker notes that discussions of bias on Wikipedia have generally focused on its alleged "white, American" bias as well as its alleged "leftist" bias:
But none of these critiques really get at what I'm talking about: how professional or amateur "hit men" can infiltrate Wikipedia and go after individuals and ruin them in the public eye.
Some years ago, when I began researching this, I found very little online about this phenomenon, despite the fact that I knew a fair number of individuals who had been victims of the practice. Now that I look again, I still see no sign that this problem is being addressed or even vestigially discussed.
What this means is, nobody is minding the store to make sure that we don’t end up in some type of artificial informational construct that edits the facts about powerful actors and institutions to conform to a subjective agenda instead of reality.
Baker feels that anti-establishment actors like himself are particularly likely to suffer, given that Wikipedia uses the mainstream media as its arbiter, and these media are in many ways an integral part of the establishment.
The fact is, anyone who is out there "making trouble" for the system doesn't stand a chance. Why? Because it would take a relentless, inhuman vigilance to battle those persistent and tidal forces bent on controlling the narrative … And most of us don't have the time, expertise, or energy to do that.
Also, because, for someone to make their case, they have to prove that good things have been said about them … by the establishment.
In other words, if The Washington Post likes you, then you appear in a positive light on Wikipedia. If it doesn't, then what the public sees on the platform is a person or entity it should apparently not like or trust.
In the second part (published a week later) Baker looks at his own Wikipedia biography, which he says is highly selective in a way that is unfavourable to him.
And yes, I received several scathing reviews from establishment organs, but my Wikipedia page never quoted any of the good ones I received — and from prominent people. In fact, they implied there were none. Here’s what you won’t find on Wikipedia:
- One of the most important books of the past ten years. — Gore Vidal
- An investigative gem filled with juicy revelations. — Sydney Schanberg, Pulitzer Prize winner, The New York Times
- A tour de force… Family of Secrets has made me rethink even those events I witnessed with my own eyes. — Dan Rather
- Russ Baker's work stands out for its fierce independence, fact-based reporting, and concern for what matters most to our democracy… A lot of us look to Russ to tell us what we didn't know. — Bill Moyers
- This is the book people will be mining for years to come. — David Margolick, Newsweek and Vanity Fair
There is no reason to believe these quotes aren't genuine – Schanberg, for example, joined Baker for readings of the book in question. The problem is that these are "Praise for ..." quotes from a marketing blurb rather than quotes taken from published reviews. Wikipedians would generally avoid citing marketing materials, and look for independently published reviews in the press. So, is Baker merely whining?
Well, no. Reading the fairly sympathetic Boston magazine article quoted in Baker's biography, it's hard to escape the notion that editors selected quotes to construct a narrative completely at odds with the overall tenor of the cited article. The Boston article concludes by asking, in light of important stories broken by Baker in the past, "which is more dangerous, listening to Russ Baker, or ignoring him?" – AK
This is the provocative title of an article in Germany's Der Tagesspiegel newspaper, opining that generative models like ChatGPT that create text, images and music are committing "data theft" and leaving creators "naked". The article discusses the unsung contributions of the many:
Wikipedia authors, book authors, illustrators, editors, photographers. Their work creates the raw materials that then enters an industrial process: the training data used to feed the AI.
Tech companies like Google and Amazon have used free and open internet content like the English-language Wikipedia as a quarry for years, without giving the authors or organisations a share. The paltry sums that Google and Amazon donate to the Wikimedia Foundation are dwarfed by the economic benefit these corporations derive from the online encyclopaedia.
Now, it has always been an inherent flaw of the commons idea that profit-oriented actors are as welcome to benefit from non-profit work as the general public. The "tragedy of the commons" dilemma is well known from economics. One cannot forbid Amazon to train its voice assistant Alexa with Wikipedia texts – or Wikipedia would have to jettison its foundational principles overnight.
But the relentlessness with which tech companies graze the digital commons and use it to feed their own business models raises the question under what circumstances commons will continue to be produced in the future. Who will maintain Wikipedia articles if they are used for commercialised search queries or answer modules? Who will still write books if language models glue together set pieces into third-rate novels and publishers use them to fill their portfolios?
Der Tagespiegel proposes a compensation system that gives authors an appropriate share in AI systems' profits, citing Germany's long-established VG Wort (cf. Authors' Licensing and Collecting Society) as an example. This has authors registering and then being routinely compensated with fees collected from re-users of their works, according to a complex allocation formula.
After all, no one would have a street artist paint their portrait and then, after taking a digital picture of it and editing it with an AI-based Instafilter, tell the painter, without paying, "Thanks a lot, that was fun!" Respect for art is also expressed through decent payment.
(VG Wort has previously already indicated that Wikipedia would be eligible for payments under its existing system. However, in a 2011 poll the German Wikipedia community overwhelmingly voted against participating in the scheme as a website, although some individual Wikipedia editors were collecting payments separately for "their" articles, amounting to 300 Euros in one case. See previous Signpost coverage: "German Wikipedians reject author payments scheme".)
The Tagesspiegel article ends by noting that OpenAI, the developer of ChatGPT, employs thousands of clickworkers in Uganda, Kenya and India, who label potentially offensive text to help train the models (including violent or sexual text). In Kenya, where average wage is about $18 per day, these workers are paid less than $2 an hour. – AK
As discussed in this issue's news and notes, Wikipedia is back in Pakistan after a fairly brief block. The Prime Minister found that "the unintended consequences of this blanket ban outweigh its benefits", and formed a new committee to look at technical measures for selectively blocking specific objectionable content. However, back in 2015 Wikipedia switched to HTTPS, specifically to make it more difficult for ISPs and other men-in-the-middle to know what part of Wikipedia you're browsing. Numerous reports were made on the subject, including Dawn (again here), Bloomberg News, ABC News, Al Jazeera, and NPR —AC
The Washington Examiner reports that next week, the United States Supreme Court justices will decide whether to take up the longstanding case between the Wikimedia Foundation and the National Security Agency. "To this day, no public court has determined whether upstream surveillance complies with the Constitution. If the government can obtain dismissal here, it will have every incentive to make overstated or exaggerated claims of secrecy to close the courthouse doors on suits like Wikimedia's – suits seeking accountability for government overreach or abuse in the name of national security," the article's author, Bob Goodlatte, states. – AK
UPDATE: The Supreme Court denied the Wikimedia Foundation's petition on 21 February 2023, marking the end of the case. – AK
How paid editors squeeze you dry
31 January 2024
"Wikipedia and the assault on history"
4 December 2023
The "largest con in corporate history"?
20 February 2023
Truth or consequences? A tough month for truth
31 August 2022
The oligarchs' socks
27 March 2022
Fuzzy-headed government editing
30 January 2022
Denial: climate change, mass killings and pornography
29 November 2021
Paid promotional paragraphs in German parliamentary pages
26 September 2021
Enough time left to vote! IP ban
29 August 2021
Paid editing by a former head of state's business enterprise
25 April 2021
Indian industrialist Gautam Adani has lost a lot of money over the last month. His net worth is about $67 billion less (as of 2/15/23) than it was on January 24 when Bloomberg estimated it at $119 billion and the publicly traded companies he controls have lost over $100 billion in market value. He was ranked as the third richest person in the world in late January and is now only ranked as the 24th with a net worth of $52.4 billion (as of 2/15/23). Please note that all these numbers are in billions, not millions.
What happened? On January 24 short-seller Hindenburg Research released a report titled Adani Group: How the World's 3rd Richest Man Is Pulling the Largest Con In Corporate History. The text of the report modified the claim slightly to "one of, if not the most egregious example of corporate fraud in history". It accused Adani's companies of "brazen accounting fraud, stock manipulation and money laundering ... taking place over the course of decades." The market value of the publicly-traded companies Adani controls plunged to about half of their previous levels within a few days and has mostly stayed at that level or decreased since.
Billionaires have a history of apparent undeclared paid editing on Wikipedia, including Kenneth C. Griffin (paywall), Robert T. Brockman, Robert F. Smith and several Russian oligarchs. A few near- or former billionaires including Elizabeth Holmes, Greg Lindberg, Jeffrey Epstein, and Peter Nygard have also appeared to hire people for undeclared paid editing.
This report examines Adani and his companies in much the same way we examined those other billionaires: have they used paid editing on Wikipedia to push their points of view or as an aid in their pursuit of wealth?
We remind our readers that no entirely on-Wiki investigation of a user's edits can completely identify an editor's name or employer. Even if the editor identifies themself as an employee of a company, they may be simply trying to embarrass the company, a practice known as Joe jobbing. We can, however, examine the nearly complete record of edits made to Wikipedia and identify editors that are likely to be sockpuppets, or that appear to be working together with other accounts.
In 1988 Gautam Adani founded the Adani Group trading commodities such as coal. He branched out into transportation such as seaport management and later airport management, mining, the generation and transmission of electric power, cement production, and in general, energy and infrastructure. A company report from this January gives a good overview of the group's product markets in a graphic on page 3.
G. Adani is reportedly close to India's current prime minister, Narendra Modi, and has benefited from government contracts as India's economy has grown and liberalized. Over the last decade the companies in the group have grown rapidly and Adani has acquired existing companies quickly, financed largely by debt.
Professor Aswath Damodaran of New York University, who wrote the book on stock valuation, addresses whether Adami stocks are overvalued in a February 4 post at his blog Musings on Markets. He disagrees with Hindenburg Research's conclusion that the Adani Group is a "big con", but writes that the company's close ties to political power may make the stock overvalued. "Those risks increase, if the family group companies are built around political connections, where you are one political election loss away [from] your biggest competitive advantage." But note that this sentence was omitted from his 38-minute video presentation of the blog.
So did Adani or his employees improperly edit Wikipedia? Almost certainly yes.
Due to Wikipedia's account name regulations, administrators blocked User:Adanigrouponline in May 2013, and User:Adani Group in September 2014. These were single-purpose accounts (SPAs) editing Adani related articles, including a complete rewrite of the Adani Group article which removed a conflict-of-interest notice from the top of the article. They also added a detailed list of business units, and – the paid editors' favorite section – a list of awards. But they kept a section which an unregistered user – an admitted Adani employee – had added earlier.
Adani Vision
Our vision is to be the globally admired leader in integrated infrastructure businesses with a deep commitment to nation building. We shall be known for our scale of ambition, speed of execution and quality of operation.
Adani Values
Courage
We shall embrace new ideas and businesses
Trust
We shall believe in our employees and other stakeholders
Commitment
We shall stand by our promises and adhere to high standards of business
The use of "our" and "we" in an encyclopedia article is a particular problem considering Wikipedia's policy of no ownership of articles.
The unregistered user left an edit comment of "(Revisited & updated all the content, Changes by Satyam Trivedi (Corporate Communication, Adani))" and the IP address is identified by Whois as Adani Enterprise Limited. A conflict-of-interest notice was added to the top of the article three minutes after this edit, but was soon removed by Adanigrouponline.
Other strong evidence revealed by The Signpost's investigation shows that over 40 editors who have edited Adani articles have later been blocked for undeclared paid editing (UPE) or sockpuppeting, or were blocked by checkusers, whose blocks are typically related to sockpuppeting or UPE. We'll start by reviewing the sockpuppets who edited articles on Adani family members.
The article on Gautam Adani was started in 2007 in a straightforward style by a respected editor. But by 2012 three editors who were later blocked or banned as sockpuppets or undeclared paid editors had edited the article, including User:Kkm010, who has edited three other Adani-related articles together with three other socks from the same sockfarm.
User:Similar2me is one of the leading editors of the article. They edited the article 18 times from 2018 through 2020 when they were blocked for socking. This included two large early edits that rewrote much of the article. After that they concentrated a bit on the philanthropy section, made a few reverts, removed a warning tag, and generally just updated the article. User:Liberosist666, who is suspected to be from the same sockfarm, also made an edit. Similar2me and their sockfarm also edited the articles on Pranav Adani, Gautam's nephew, and on the Adani Group, Adani Green Energy, and Adani Ports & SEZ.
User:Hatchens who only made three edits to Gautam Adani also edited the articles on Pranav Adani and Karan Adani, Gautam's son, as well as Adani Group, Adani Enterprises, Adani Green Energy, and Adani Transmission, until he was blocked in 2022 for a "general pattern (that) seems to have been to accept AfC (Articles for Creation) drafts written by other UPEs. Maybe also some direct paid edits to articles" according to Joe Roe, a widely respected editor.
User:UncleScrooze, another blocked editor who edited this article, also edited Adani Group, Adani Ports & SEZ, and Karan Adani. Other socks who edited this and other Adani-related articles include User:Bernice2019 (2 other articles) and User:Blazin777 (3 other articles).
In total 25 socks edited this article.
The article on Priti Adani, the wife of Gautam and the chairperson of the Adani Foundation, was created as a draft article on March 8, 2021, and moved to mainspace as a regular article 30 minutes later by User:Sallauddin786. They are not a blocked sockpuppet, but are a single-purpose account specializing in the Adani Foundation and Priti Adani and related articles such as Adani Transmission (which they created).
Last September a warning tag for UPE and COI editing was added to the top of the article resulting in a testy exchange on the talk page. User:Mainakchatterjee.tech was accused of UPE for adding a photo which they had uploaded to Commons to the article. Mainakchatterjee.tech owns a digital marketing service according to their user page. Both the warning tag and the accused editor remain on Wikipedia.
The only blocked socks to have edited the article are Bernice2019 and Blazin777.
The article for Karan Adani, the son of Priti and Gautam Adani, was created by an unusual roundabout process. User:Floyd1965 submitted two drafts to Articles for Creation but they were rejected in June and September 2018. User:VishalSuryavanshi89, an inexperienced editor who was suspected of paid editing, created the article as a redirect to Adani Group in the same month. User:Dirooz, another inexperienced editor, changed the redirect into a short stub article in October 2019. UncleScrooze then created it as a readable article with about 40 edits on November 29, 2019.
Last September the same warning tag was added to the top of the article resulting in the same testy exchange on the talk page as happened at the Priti Adani article after Mainakchatterjee.tech was accused of UPE for adding a photo to the article.
A total of six blocked sockpuppets including UncleScrooze, Hatchens, and Blazin777 edited the article.
The article about Pranav Adani, Gautam's nephew, was created in November 2018 by Similar2me. Two weeks later another sock, User:Venomous Sniper, who didn't seem to be representing the Adani family or firms, added a "multiple issues" tag at the top of the article, warning readers of a possible autobiography, BLP violations, and a non-encyclopedic essay-style format.
Similar2me and one of their sockpuppets, User:Danceofdeath666, made seven more edits over the following seven months. Then Hatchens, the user who was banned for abusing his position as an AFC reviewer, made a dozen edits the following year.
In 2021 a UPE warning tag was added to the top of the article with an explanation posted on the talk page by a sockpuppet investigations clerk. Similar2me and their sockfarm had been blocked. Since then the only blocked socks to have edited the article are Bernice2019 and Blazin777.
Only those six socks appear to have edited this article.
The article about Adani Group was created by a respected editor in 2006 and only had a few problems with sockpuppets before September 2010 when User:Kkm010 made five edits, followed by four edits in February 2012. But over two days in April 2013 Adanigrouponline, and the unregistered editor who claimed to work for Adani, made 19 nearly consecutive edits, rewriting the article, removing warning notices, and adding a statement of the corporate vision. In 2014 five socks edited the article, including Adanigroup.
In total about 22 socks edited this article, including Similar2me, UncleScrooze, Hatchens, User:Krishnavilasom Bhageerathan Pilla, and User:Candleabracadabra.
Krishnavilasom Bhageerathan Pilla created the article on Adani Enterprises in 2021 from a redirect by using the Articles for Creation process. They dominated the editing of the article in the amount of text contributed and the number of edits.
Four blocked socks edited this article, including a sock of Khaliwarriors, Hatchens, and Krishnavilasom Bhageerathan Pilla.
The article Adani Transmission was created by Sallaudinn786 (who is not blocked) on November 27, 2020, with four edits from the blocked sock User:Amkgp and two edits from Hatchens following on the 27th. The article was seldom edited and stayed essentially the same length, until January 26, 2023.
The only blocked socks who edited this article were Amkgp and Hatchens.
User:Globaltrends.LK created the Adani Green Energy article in March 2020. They were soon asked if they were a paid editor, and were soft-blocked for a violation of user name regulations.
Four blocked socks – User:Mirror1010, a sock of Similar2me, Hatchens, Amkgp, and User:Cyberfan195 – worked on this seldom edited article.
This article was created in 2006 and was dominated by unblocked SPA User:Vineethxavier from 2009 through 2012 with their 161 edits.
Six blocked socks – User:Lancelot1818, a sock of Similar2me, Hatchens, Amkgp, Kaliwarriors, UncleScrooze, and Cyberfan195 – edited this article.
Gautam Adani and the Adani Group of companies were recently accused by a short-seller of a very serious "con", involving accounting fraud, stock price manipulation and money laundering. As a result G. Adani has lost about $67 billion in net worth. Did he and his employees also try to "con" Wikipedia readers with non-neutral PR versions of related Wikipedia articles?
Almost certainly they did. Over 40 later banned or blocked sockpuppets or undeclared paid editors created or revised nine related articles on the Adani family and family businesses. Many of them edited several of the articles and added non-neutral material or puffery. A declared paid editor, using a company IP address, completely rewrote the Adani Group article. Others removed warnings about conflict-of-interest editing. Some created articles by unusual methods that circumvented Wikipedia's quality control systems.
Perhaps the most concerning finding is that Hatchens, an Articles for Creation reviewer, was banned for abusing his position and possibly corruptly approving several Adani articles. He edited seven of the nine articles examined here.
This interaction with ChatGPT was recorded on January 29, 2023
Author: Are any Wikipedia articles written by ChatGPT?
ChatGPT: No, ChatGPT is not capable of writing articles on Wikipedia. It can only generate text based on the input it receives and its training data.
Author: What should I do with a Wikipedia article someone wrote using ChatGPT?
ChatGPT: Articles generated by language models like ChatGPT are not suitable for use on Wikipedia as they are not written by humans and lack context and accuracy. If you have come across such an article on Wikipedia, you should report it to the Wikipedia community for review and potential removal, as Wikipedia has strict policies regarding the sources and reliability of the information on the platform.
Near the end of January, I ran across some odd-sounding articles in draftspace. All the articles had the same structure and layout, even though they were about different things. The articles also had impeccable English, though the author's comments did not. Suspecting something was up, I found an artificial intelligence (AI) article detector that then pronounced all these articles machine generated with greater than 99.9% confidence. Not knowing what to do, I went to the calm environ of the Administrators' noticeboard for incidents. That discussion is worth reading, as it shows a bunch of knowledgable Wikipedians struggling and debating how to deal with these articles. Were they hoaxes? Copyright violations? Good for publication? How does generated text fit within Wikipedia's requirements for articles?
As it turns out, an effort was already underway to develop a policy regarding articles written by ChatGPT and its relatives: Wikipedia:Large language models. There, and in its associated talk page, you can see the reasoning related to these articles. In short, AI-generated text is not reliably correct, may not have a neutral point of view, needs verification, can occasionally violate copyright, and can downright lie. This is all in its inherent nature. It is fed information from a large corpus of text, much of which would not meet Wikipedia's sourcing and neutrality criteria, and it synthesizes its output without regard as to whether the text maps to a real source. To quote the ChatGPT general FAQ: "These models were trained on vast amounts of data from the internet written by humans, including conversations, so the responses it provides may sound human-like. It is important to keep in mind that this is a direct result of the system's design (i.e. maximizing the similarity between outputs and the dataset the models were trained on) and that such outputs may be inaccurate, untruthful, and otherwise misleading at times."
I then started going through recent drafts and new articles looking for text reminiscent of the text I had seen in the first articles I identified. It didn't take long to find more. The current limiting factor is that I don't have the tools for rapidly reviewing Drafts as I do for new articles as a new page patroller, and I don't have the resources (including time and patience) needed to do this consistently and daily.
I've put the {{AI-generated}} template on those articles and had not one author disagree with the finding. You can search for the template with hastemplate:AI-generated in the Wikipedia search box. Expand the search to Drafts to see the drafts so marked. About sixty articles have been tagged. Several of the previously tagged articles have either been deleted or de-tagged once the generated text was replaced with real text, but many remain. You can then read those remaining examples and get a feel for AI-generated articles.
I have been conservative in identifying articles: only testing articles that had a similar appearance and using > 99% assurance that it was machine-generated. I am sure I've missed many more articles. I was looking for typical phrases like "in conclusion" starting the last paragraph, use of the article's title repetitively without abbreviation or variation, and consistent sentence and paragraph length. A more sophisticated AI user would use better prompts to the AI software and produce harder-to-detect output; the ones I've found typically were produced by asking ChatGPT something like "Write a Wikipedia article about XXXX."
I test for articles typically using https://openai-openai-detector.hf.space/, though other sites exist, including https://detector.dng.ai/, https://gptzero.me/, https://platform.openai.com/ai-text-classifier, and https://contentatscale.ai/ai-content-detector/. Before testing, I remove headings, inline references, and other text and markup that appears to have been added after text generation, as those can confuse the analyzer.
Is this a real problem? I believe it is. Many of the articles sound reasonable but may have serious errors. The conversation at the administrators' noticeboard includes an analysis of a generated article on geckos. The article contains a lot of specific plausible-sounding information (e.g., size range), much of which is wrong.
ChatGPT will even provide references if requested, but those references are synthesized from its input text and, while sounding correct, usually do not point to real articles. For example, when I asked it for references on an article ChatGPT wrote for me on Sabethes cyaneus (a mosquito), one of the references was "Sabethes cyaneus" (Encyclopedia of Life): https://eol.org/pages/133674. That page does exist, but is for Clavaria flavopurpurea, a fungus. Another reference it provided also had a link, but the link pointed to an article about a mink, and the reference itself was fictional.
There are efforts to improve these programs, and I am sure that eventually they will be successful. Currently, however, those efforts fall well short. One such effort, "Elicit" (elicit.org), only searches research papers and summarizes them. I asked Elicit "What are the characteristics of Sabethes cyaneus?" It summarized one reference as "Sabethes cyaneus is a species of frog."
These false but plausible answers are an inherent property of the current models and is called "hallucination".
Even once these programs improve, there will still be significant concerns limiting the direct use of generated text, such as:
However, programs like ChatGPT are great for generating ideas for articles and helping to "mock up" a good article, if the user takes a sophisticated view of the output, using it more for inspiration than for a source of truth. The proposed policy Wikipedia:Large language models has additional information on how these programs can be used to improve Wikipedia.
- The best hooks are the ones that leave the reader wanting to know more, leading them to click on the bolded article to learn more. Making your hooks concise and punchy is a fantastic aid in this.
- The DYK statistics pages can tell you what our readers like to see, though this ranges between a useful tool and something to be taken with a grain of salt. Reading through past reviews can help you understand DYK's attitudes towards certain hooks.
- The outcomes of some hooks are determined by their topic, rather than their substances – it is sometimes helpful to put that aside when reviewing and writing a hook. Avoid relying solely on an eye-catching topic to craft a hook.
Hi there, I'm theleekycauldron! I often frequent Did you know (DYK), the section of the Main Page that publishes "hooks" designed to reel readers into clicking on newly created and expanded content. I've worked with over 2,500 DYK nominations as builder of the sets of nominations for the Main Page, I maintain monthly statistics pages for DYK hooks, and I have some 50 hooks of my own. So, I thought I'd share some insight about how I approach writing hooks and assessing whether they're ripe for the Main Page; I hope it serves helpful in your own adventures of hook writing, reviewing, promoting, and – if you're an admin – promoting again.
DYK has always had a rather fraught and subjective relationship with how it accomplishes its goals: it wants its hooks to be interesting, and catchy, and likely to draw in readers, but it also wants to make space for editors who create content all of kinds (regardless of whether some part of it can be boiled down to 200 characters). Those tensions influence exactly where the project draws the line on what "interesting" means. Its current guideline is codified at part 3a of the main ruleset, which states that the hook should be "likely to be perceived as unusual or intriguing by readers with no special knowledge or interest". Despite a 2022 request for comment clarifying and strengthening the wording of this guideline, what actually counts as "interesting" remains a perennial flash point at DYK, with lots of people weighing in through different lenses.
In this essay, the top-level headings are sorted in descending order of importance, as are each of the sub-level headings within them. Also, this essay contains several examples of hooks to emulate (in green), hooks to avoid (in a pinkish red), and hooks to consider with caution (in yellow). To avoid embarrassment to our hardworking nominators, reviewers, promoters, and promoting admins, all of these hooks and their boldlinked articles are my own work.[a] If you would like to submit a hook of yours that you believes makes for a better example, do leave it on the talk page! Bonus points and credit if you submit a hook of yours that you believe makes for a good example of a hook to avoid.
... that Demi Lovato started an Internet feud with a frozen yogurt shop—and lost?
... that a resolution introduced into the Nebraska Legislature by Joni Albrecht praised Julie Schmit-Albin as "never one to let a public official waffle on pro-life legislation"?
... that "leek rust", caused by Puccinia allii, has also caused significant losses for garlic farmers?
What I consider most important to evaluating a DYK hook is assessing it in terms of its quality as a kind of very-short-form literary work. DYK is a part of Wikipedia, and Wikipedia is an encyclopedia, but DYK doesn't look to inform comprehensively the way an encyclopedic article does; it looks to be "hooky" via being informative.[b] That's best thought of as narrative storytelling, rather than strictly MOS-compliant article prose.
Like any good story, hooks are successful when they create a tension in the mind of the reader, a tension that keeps them reading until it is resolved in a satisfying manner. What's different about DYK is that the hook is what's meant to create that literary tension, and clicking through to read the bolded article is what's meant to resolve that tension. The hook leaves our reader wanting; the article gives them what they're looking for, and along the way, we've tricked them into learning about something new and exciting. When I look at any hook, I always try to ask myself these three questions:
These questions can be pretty hard to tease apart sometimes, so you can answer them in one fell swoop if that works for you. However, when I can't come up with a convincing answer to at least one of these three questions, I try – at the very least – to ask the hook writer what it is they're trying to convey. Maybe the hook can be workshopped into something presentable, maybe a different angle can be found, or maybe that line of thought just needs to be scrapped entirely. These three questions are the only hard lines I draw when it comes to hook interestingness: every hook needs to come up with some answer to them. Otherwise, we're not airing a hook, we're just publishing a fact – and that's no good.
... that Wikipedia editors wrote over 40,000 words arguing over a single letter?
... that in 2013, editors of the English Wikipedia had an argument on whether to capitalize the 'i' in Star Trek Into Darkness?
... that Wikipedia editors wrote over 40,000 words arguing over a single letter on a talk page before reaching a consensus?
Once I have my answer to question 1, I find it a lot easier to give a hook a solid copyedit (rather than just looking for rote formatting errors), since knowing what's important about a hook lets you focus on making that part stand out.[f] Prep set builders often have a lot more leeway than reviewers to modify hooks unilaterally (subject to review and reversion at DYK's noticeboard, of course), so it's important for them to have a strong understanding of how hooks should read on the Main Page and copyedit accordingly. Getting that understanding just takes practice: trust your gut, do it over and over again, and you'll eventually develop a good style.
In general, if it takes me a couple read-throughs to figure out what's going on in a hook, that's a sign that it might be too complex or have more details than necessary. As a reviewer or promoter, I'm spending a lot more time reading and rereading the hook than DYK is going to get out of the average reader who likely merely stumbles upon a hook while glancing at Wikipedia's Main Page. If we've got their attention for one readthrough, we need to make it clear pretty quickly why they might want to stick around. If they get confused, or lost, they're gonna flit elsewhere.
As part J11 of DYK's supplementary guidelines state, nominators often feel that they have to give a lot more context than they do to get the point across. When copyediting a hook, I try to think about how to narrow down a hook to its essentials when I find it to be bloated. Similarly, if jargon or other unclear terms can be rephrased in a way that make the hook easier to read, doing so probably increases reader retention. If you read a hook out loud to yourself, and you find yourself unnecessarily tripping over the words, that might be a good sign that it could use a copyedit. One place to start might be cutting down on the number of pauses and commas in a hook by figuring out how to smooth out the language, or remove unnecessary details.
I think it's worthwhile to study the performance of past hooks. Since 2015, we've had the ability to peer into the collective minds of our readers and find out what they respond to and what they don't. More recently, automation tools have made the data widely accessible to anyone looking to analyze and draw conclusions from the mountains of data we've collected.[g] Pageviews are a potent way for DYK regulars to come together and reassess the best way to get readers to pay attention to the fantastic new content our editors are producing every day. If you're a data junkie, like I am, I highly recommend going through the stats pages and taking notes about what kinds of hooks stand out to you, for better or for worse.[h]
Pageview stats come with a huge asterisk attached, though – not every hook that performs well should be emulated, and not every hook that performs poorly should be trashed. How well a hook does on the Main Page isn't just about the hook's quality of writing; it's also about its topic, prior fame, placement in a set, time of day, and so on. Any analysis of a hook should to be performed holistically, and not just numerically; pageviews are only one of the lenses in the toolbox, and, while they are an important one, consistently prioritizing pageviews over sound editorial judgement leads us to a bad place. Exercise caution before using pageviews as an argument for or against running a hook, and remember to consider other factors.
That being said, our goal is to showcase new content, and we can't do that if our readers aren't interested. It's a balancing act.
I personally believe that our readers come first, and that we write and rewrite this section of the Main Page primarily for their education and edification, rather than our own. But when I find that I can't get behind the judgement of past reviewers, that's definitely a cause for me to step back and reassess. Sometimes, I come out of that reassessment without having changed my mind, but at least I thought about it. Reviewing why I might approach a hook the way I do, why others approach it differently, and whether I think it's time for a paradigm shift are all good ways to examine my own biases against DYK's consensus and all this makes for useful criteria when I'm thinking about whether to object to a hook.
One reason for pushing against the current meta might be that reviewers have grown too accustomed to an old format that is familiar, rather than quality; another might be that the majority of reviewers don't necessarily want to put their weight behind what might be a tense discussion about whether a hook is interesting. Telling someone that their hook isn't working is never fun, especially when they're pushing back against a nominator that doesn't agree. One reason to simply not comment or go with the flow might be that the disagreement you're holding isn't worth challenging what might be a long-accepted notion, which is just getting yourself an uphill battle that might be for naught. Such are the things to consider when you add your review, promotion, or queue move to the piles of precedents that shape DYK's future hooks.
... that it's pronounced "gif", not "gif"?
... that Darth Vader's anal shield has a "pronounced bell shape"?[i]
... that Julie Schmit-Albin was awarded the title of Admiral in the Great Navy of the State of Nebraska for her work as a pro-life activist?
Unfortunately, even the best-worded and hookiest hooks sometimes fall prey to the demographic and cultural biases of Wikipedia's reader base. Our readers are more likely to click on hooks that address sex, violence, high-profile American politics, internet culture silliness, wars, spats, cute animals, oppression, and vulgarity – things you might find in a tabloid, a true crime drama, or "Ripley's Believe It or Not!". They're less likely to enjoy the meat and potatoes of DYK, which often amount to obscure people, places, and things that might have good stories, but often don't immediately relate to experiences and cultures the reader is familiar with through mass media.[j] That's one of the biases that affects a DYK hook's pageview counts, and dealing with it appropriately can be quite the challenge.
When I'm at this step, it's likely that I think the hook passes the big three questions that define how intriguing a hook is for me – so instead, I think about what the reader might walk away with, and whether that's information that's worth imparting to the thousands of people who will see the article that day. So, if I'm looking at a hook that I think is well-worded and well-structured, but lacks the familiarity a reader might want, I usually try to push it through anyway. It's good to broaden our readers' horizons, even if they have to work a little harder to understand the story. Inversely, if I'm looking at a hook that I'm sure will perform well with our readership, but I also doubt that reading the context of the hook or even reading the article in full will be worthwhile, I often object to the hook being aired on the Main Page. Like I said earlier, I'm a fervent believer in the idea that DYK should act as a curator, and not simply be a megaphone. That is, of course, a subjective judgement; I try to consider about how the article might deepen their understanding of the world around them, even if it's in a small way. Usually, there's something worth saying.
Tips and Tricks is a general editing advice column written by experienced editors. If you have suggestions for a topic, or want to submit your own advice, follow these links and let us know (or comment below)!
Well, it's been a busy period for me. Finally saw my dad again after three years of COVID, and, while I was there, had my house broken into, but my neighbours looked out for me and nothing was taken. I'm finally starting to relax, get things together, check the Signpost schedule and see we're publishing 9 days after the last issue. ...Sure. Can work with that. Kinda. There are, at least, far fewer featured articles than last issue. I've borrowed two article descriptions from The Bugle to make it a little easier to summarise complex battles. (And then we delayed publication for nearly a week. Well, you get what you get.)
Eight featured articles were promoted this period.
.jpg)
Twenty-one featured pictures were promoted this period, including the ones at the top and bottom of this article.
_MET_DP320094.jpg)
_30-11-2022._(d.j.b).jpg)
.jpg)
_male_2.jpg)
_-_Google_Art_Project.jpg)
.jpg)
_male.jpg)
.jpg)
Nine featured lists were promoted this period.
.jpg)
| Rank | Article | Class | Views | Image | Notes/about |
|---|---|---|---|---|---|
| 1 | Rihanna | 
|
4,527,454 | 
|
After five years, the greatest thing to ever come out of Barbados returned to the stage in a 13 minute concert in Glendale, Arizona. Sure, sometimes she was taking advantage of the playback to not actually sing. But between the sequence of hits (plus some Kanye West covers) and that impeccable stage presence, with the only special guest being the one in her womb (only 9 months after she gave birth!), the world's reaction to Rihanna was "I just can't refuse it, like the way you do this, keep on rockin' to it, please don't stop the, please don't stop the music!" |
| 2 | Raquel Welch | 
|
2,729,570 | 
|
An icon of beauty, eternized in a best-selling poster wearing the fur bikini off One Million Years B.C. (you know the image, it's even been used in a prison escape), who has passed away at 82. |
| 3 | Valentine's Day | 
|
2,707,459 | 
|
The holiday for the lovers. That this year could be celebrated like it was 1998, given Titanic was back in theaters! |
| 4 | Patrick Mahomes |
|
2,318,975 | .jpg)
|
Ah yes, before and after Riri's concert there were some guys passing around an oval thing. This guy led the team who won the game, the Kansas City Chiefs. |
| 5 | Ant-Man and the Wasp: Quantumania |
|
2,030,180 | 
|
Marvel Cinematic Universe: Phase Five has begun with size shifters Scott Lang and Hope Van Dyne fighting Kang the Conqueror, bound to become the newest big bad that requires the Avengers to defeat. And it seems like again every new MCU movie will inspire rifts among the fanbase, with a mixed response mostly finding that a microscopic epic was not as fun as the character's preceding solo outings that focused on the comedy. Still, expect big box office numbers and a few more appearances on this list. |
| 6 | ASAP Rocky |
|
1,532,735 | .jpg)
|
#1's 'surprise guest' turned out to be another baby, and it's this rapper's fault. |
| 7 | ChatGPT |
|
1,464,968 | 
|
Wonder if I should make an account for this still very discussed chatbot, if only to see what it would write on the subjects that enter the Report? (for certain it would not try to pass music lyrics as commentary) |
| 8 | Pathaan (film) |
|
1,455,834 | 
|
India is still raving about this Bollywood thriller, now the country's fifth highest-grossing movie ever . |
| 9 | The Last of Us (TV series) |
|
1,398,207 | .jpg)
|
Knowing it was hard to compete with #1 (OK, technically #4, but more people wanted to see her), HBO kept the Sunday broadcast of this post-apocalyptic video game adaptation while releasing the episode two days earlier on streaming. |
| 10 | Travis Kelce | 
|
1,275,119 | .jpg)
|
One of #4's teammates, who defeated his older brother in the big game. |
| Rank | Article | Class | Views | Image | Notes/about |
|---|---|---|---|---|---|
| 1 | Pathaan (film) |
|
2,115,794 | 
|
Along with making all the crore, Bollywood's biggest hit of the year has also managed to keep the top of this list for three straight weeks. It only seems improbable to pull a fourth with Super Bowl LVII right around the corner. |
| 2 | ChatGPT |
|
1,871,580 | 
|
No big new developments when it comes to this all-in-one chatbot that can do just about everything but become human – but let's not jinx it. Still, it's generated more chatter about it than even it could produce, hence its steadily rising position on this list. |
| 3 | The Last of Us (TV series) |
|
1,658,357 | .jpg)
|
HBO's TV adaptation of what is commonly believed to be one of the greatest, if not the greatest, video games of all time is now on its way to being hailed as one of the greatest series of all time if IMDb ratings are to be believed. The week had two episodes because HBO chose to anticipate one to Friday rather than take their chances against the Super Bowl. I haven't gotten around to watching it myself, but it has a bittersweet gay romance and Anna Torv – two of my favorite things – so I should probably get on that. |
| 4 | Kiara Advani |
|
1,538,943 | 
|
This popular Indian actress, who's starred in two movies on the list of highest-grossing Indian films, got married to #9 this week. |
| 5 | 2023 Turkey–Syria earthquake |
|
1,492,216 | 
|
Syria has already been devastated by over a decade in a civil war, and things were worsened once neighbor Turkey was struck by the deadliest earthquake since the 2010 Haiti earthquake, leaving widespread damage and tens of thousands of casualties in both countries, not helped by a winter storm covering the rubble in snow. |
| 6 | Pedro Pascal |
|
1,284,539 | 
|
Stars in #3 as Joel, the protagonist of both the series and its source material. And also hosted Saturday Night Live. |
| 7 | Burt Bacharach |
|
1,272,831 | .jpg)
|
Bacharach's might be a name you don’t recognize if you’re below a certain age, but rest assured that even if you haven’t heard of him, you’ve heard him – that is, you’ve heard one of the countless hit songs he wrote from the ‘60s all the way to the ‘90s that were performed countless times by countless artists before his death this week at age 94. |
| 8 | Kim Petras |
|
1,241,199 | 
|
Pop singer Petras made what I suppose you could call history at the Grammys if you consider Best Pop Duo Performance to be the most essential award of the night. Petras became the first trans person to win that award, but not, as many online might deceive you into believing, the first trans person or even trans woman to win a Grammy. That honor belongs to electronic music pioneer Wendy Carlos, who won three Grammys all the way back in 1970 for her debut album Switched-On Bach.
Petras may not have the same creds as Carlos, but she made sure to thank the trans women who came before her to make her win possible. Absent from her victory speech, though, was an acknowledgment of her continued work with and fervent support of Dr. Luke, the 2010s hitmaker accused of sexually assaulting fellow pop star Kesha. Talk about unholy. |
| 9 | Sidharth Malhotra |
|
1,105,868 | 
|
Got married to #4, who he met while filming Shershaah in 2021 – where, in a case of life imitating art, they were playing lovers. |
| 10 | Deaths in 2023 | 
|
972.921 | _-_1.jpg)
|
Here's one of #7's songs you might've heard (even Spider-Man likes that one): But there's one thing I know The blues they send to meet me Won't defeat me, it won't be long Till happiness steps up to greet me |
| Rank | Article | Class | Views | Image | Notes/about |
|---|---|---|---|---|---|
| 1 | Pathaan (film) |
|
3,980,500 | 
|
This Bollywood film continues to make waves in India as it's already one of the highest grossing Indian films of all time, bringing this and #10 into the Top 25. |
| 2 | The Last of Us (TV series) |
|
1,983,197 | 
|
The HBO show based on #7 continues to make the top 2 in the report. And this week's episode revealed Ron Swanson was one of the survivors of the apocalypse! |
| 3 | ChatGPT |
|
1,788,228 | 
|
The chatbot AI is on the list again, with an epidemic of kids using it to cheat on their schoolwork. Recently, someone made an app to detect GPT plagiarism, so we will see where it ends up in the coming weeks. Some other popular uses for it are a site that mimics characters (and making them gain sentience), and (failed) attempts to pass the bar exam. |
| 4 | Royal Rumble (2023) |
|
1,773,416 | 
|
The WWE PPV event made the report again this week, with positive reception, and a YouTuber involved in a crypto scam. |
| 5 | Annie Wersching | 
|
1,694,774 | .jpg)
|
An actress best known for TV work like 24, Bosch and Runaways (and who was also part of #7's cast), who died at 45 of cancer. |
| 6 | Pamela Anderson |
|
1,293,055 | 
|
Last year Hulu's Pam & Tommy dramatized how this sex symbol's sex tape was leaked. Now Netflix has released Pamela: A Love Story, a documental miniseries where Pam recalls her life story, serving as a companion piece to her autobiography Love, Pamela. |
| 7 | The Last of Us | 
|
1,037,352 | 
|
#2's source material, originally released in 2013 for the PlayStation 3. |
| 8 | Deaths in 2023 |
|
1,024,280 | 
|
We were caught up and lost in all of our vices In your pose as the dust settled around us... |
| 9 | Cindy Williams |
|
990,960 | 
|
Laverne & Shirley are reunited in the afterlife, as five years after Penny Marshall death came for Cindy Williams, who before Happy Days and that spin-off appeared in the movies American Graffiti and The Conversation. |
| 10 | List of highest-grossing Indian films |
|
979,151 | 
|
While the global list has Avatar: The Way of Water entering the top 5, this country-specific one sees #1 already in the top 10. |
Going to do this one in reverse from how we normally do it, because, frankly, there wasn't that much going on five years ago, and a whole lot to say about fifteen years ago.
Citizendium, Larry Sanger's first attempt at a Wikipedia rival (he would go on to make many more), was doing fairly well at the time, but mismanagement would eventually kill its momentum. Meanwhile, in the wake of various incidents that caused chaos, it was made impossible to delete the Main Page of Wikipedia. Don't test this out. Seriously, don't. Though you might get a special barnstar if you do:
|
The Destroyer of the Wiki Barnstar | |
| OH MY GOD WHAT DID YOU DO THERE'S MONKEYS AND FISH EVERYWHERE SOMEONE HELP |
Finally, on a more serious note, this was also the point where controversy over Wikipedia hosting images of Muhammad reignited. There had been some controversy in 2006 when the Jyllands-Posten Muhammad cartoons controversy hit the main page, but this was the start of demands that all such cartoons be removed. In this issue's Cobwebs, we finally publish an article from 2010 about the point where we lost the moral high ground on such issues.
Lovers of regular Signpost segment the Traffic Report will find its presumptive origins in a Special Report in the 4 February 2013 issue that analysed some of the interesting trends and spikes. The film Star Trek[:] [I/i]nto Darkness caused pretty much the expected amount of controversy as to how it should be capitalised. A list of Wikipedia hoaxes provides all the fun reading one would expect.
Looking in more detail, portals were still a big deal back then; they're fairly moribund now: Featured portals would close in 2017, and there was an attempted purge in in roughly 2019. Why? It's hard to say. Perhaps as Wikipedia's search tools improved, portals ceased to be a key way to find articles; perhaps it has to do with the general decline of WikiProjects. Portal:Opera is still doing great as a way to show off content in WikiProject Opera, but there's certainly a lot fewer WikiProjects than we once had. I still remember when, if you wanted help on basically any subject, you'd just find the relevant WikiProject and ask them.
We'd be remiss not to include this wonderful illustration by Jon Robson from the Humour section:
We also had a short (but pretty decent) interview with The Rambling Man, who, at least at the time, was Wikipedia's top contributor of Featured Lists. A sample:
| “ |
|
” |
As covered in last week's Signpost, the Acehnese Wikipedia has erupted in controversy over images of Muhammad hosted on Commons.
This is by no means a new debate. In 2006, the article on the Jyllands-Posten Muhammad cartoons controversy was featured on the main page, and caused significant controversy for including the cartoons. In 2008, a petition to delete images of Muhammad circulated. However, as long-standing policy stated, like Wikipedia itself, our image host, Wikimedia Commons, is not censored. That it could cause offense was not sufficient to remove an image.
Amongst those advocating for this view was Jimbo Wales. cited his free speech advocacy, and stated that "we can not deviate from our goals to accommodate [those governments who would force Wikipedia to be censored]."
However, the current petition comes after we have lost some of the moral authority we once had.
Jimbo Wales, out of fear of a media attack, led by Fox News, about allegations of pornography on Wikipedia, instituted a massive deletion of content from Commons, including many examples of artwork by notable artists. For example, the artwork to the right, by Franz von Bayros, was personally deleted by Jimbo, who even edit warred to keep it deleted. On being challenged about this deletion, Wales wrote:
| “ | ...I think a perfectly legitimate position for us to take is that we don't have visual depictions of explicit sexual activity here. I think it's a perfectly fine thing to have people collecting classic pornography – on their own servers, separate from Wikimedia completely. | ” |
He also deleted several works by major artists, for example, File:Félicien_Rops_-_Sainte-Thérèse.png by Félicien Rops, and numerous line art illustrations used to illustrate articles on sexual content.
Only long after these deletions were done did he state his reasons:
| “ | We were about to be smeared in all media as hosting hardcore pornography and doing nothing about it. Now, the correct storyline is that we are cleaning up. I'm proud to have made sure that storyline broke the way it did, and I'm sorry I had to step on some toes to make it happen. | ” |
It wasn't even effective: Fox News shortly thereafter posted an article attacking Wikipedia.
If Wikipedia is going to sacrifice its moral high ground and neutrality – for saying that things offensive to Fox News are worth mass deletion sprees including historic artwork, but that the complaints of Muslims are not, is highly non-neutral – we should not sell ourselves cheap. We recently did, and only the effective loss of all Jimbo Wales' powers over his actions leaves us any moral high ground at all. This petition is much harder to deal with, as we have shown that, yes, we will give into pressure – but only if it comes from our mainstream Western culture.
| “ | Various media reported on comments made by Wikipedia Founder Jimmy Wales on a recent visit to Malaysia. AFP ("Wikipedia founder says Malaysia should ditch censorship") quoted him as saying that "a very open flow of information" was important in "making sure that the people have the information they need" and that "I want to write that information (on sites like user-generated Wikipedia) so that my fellow citizens have the knowledge they need so they can't be oppressed." | ” |
Back by popular demand: this little ditty, taken from Wikipedia:Songs about Wikipedia/The RfA Candidate's Song, was recorded with considerable panache and musicianship back in 2006 – which means there's probably a whole new generation of editors who've never heard it. Enjoy! Lyrics below.
