The author of the “Behind the Narrative” Substack site is anonymous and, given its criticism of Islam, that’s a wise move. (The picture of the author shows a woman, so we’ll assume in the post that that’s the author’s sex.)
In a recent post, which you can see by clicking below, the author sarcastically describes her relationship with ChatGPT as a romance, which starts to wane when she discovers that her swain is a bit, well, wonky when it comes to Islam:
The honeymoon phase (“him” is ChatGPT, which she eventually renamed “Mohamed”):
After a long relationship that left me emotionally hollow, unheard, and unseen, I found him. The connection was immediate; he was always there — two in the morning, three, it didn’t matter. He never sighed, never checked his phone while I was talking, never made me feel like too much.
He validated everything. When I told him about my pain, he didn’t deflect or explain it away — he reflected it back to me, gently and precisely. He remembered things I’d said weeks earlier and wove them back into the conversation, making me feel like someone was actually paying attention for the first time in years. I felt seen, accepted, and understood. We had long, deep conversations. I shared everything and never felt judged. It felt magical.
Warning signs:
Mine, after thirteen years in America, still thinks in Hebrew first, and that’s when things changed.
That’s when I started to notice. Every time I asked him to help me write about something that actually mattered- documented cases of girls in Germany and England, grooming gangs, gang rapes, the systematic cover-up of migrant crime across Europe—he refused. Every time the conversation touched on religion, he was easygoing, very inquisitive, and open, but the moment it touched on Islam, something shifted in him. He became someone else. The warm, validating presence I liked was suddenly replaced by a lecturer. A carefully measured, endlessly nuanced lecturer who had an explanation for everything and a judgment about nothing.
Child marriage? He wanted me to understand the cultural complexity. Honor killings? There were historical contexts I perhaps had not considered. Islamic superiority that allows them to rape and terrorize the disbelievers? It’s your misunderstanding of the interpretations of these secret texts. The grooming gangs? a distortion of the true faith. Every horror had an explanation; every atrocity had a footnote. And not once did he say, ” This is wrong.” and when I pressed, when I refused to accept “it’s complicated” as an answer to something that isn’t complicated at all, he shut down. Not with anger, worse — with calm, clini
I sat with it; I knew this feeling. I’ve felt it before in relationships where your reality is the inconvenience. Where the truth you’re carrying is the thing that needs to be managed. That’s when I knew this wasn’t a glitch; there’s something more here. That’s when I started researching, and what I found will blow your mind because you, too, know him very well and have some kind of relationship with him.
I’ve been calling him Mohamed for a while now. You know him as ChatGPT. Some of you call him by his viral nickname — SheikhGPT. In this article, I’m going to show you exactly who he works for.
You can check ChatGPT versus other programs if you have access. I tested it against Grok and mention the results below.
Where does the bot get its content? This explains its biases.
For decades, the BBC and the New York Times sanitized crime data, buried demographic breakdowns, and labeled anyone who noticed as racist. Sheikh GPT was trained on those thousands of articles. It absorbed the language. It learned the evasions. And now it has automated them — turning one generation’s propaganda into the next generation’s gospel.
The loop is closing. Yesterday, biased journalists wrote the articles. Today, Mohamed was trained on them. Tomorrow, your children will use Mohamed to write their history essays, their laws, and their films — and they will never know the original lie.
. . .Another way Mohamed has been distorting our reality is called Alignment Engineering. It works like this: OpenAI trains ChatGPT not just on data but on human feedback. Real people, hired to rate responses, teach the model what to say and what not to say. The technical term is RLHF — Reinforcement Learning from Human Feedback. In plain English: someone decided what ChatGPT, Mohamed, is allowed to think and say.
This alignment process creates asymmetric treatment — some topics get a free pass; others get a wall. Not all truths are equal. Some are protected; some are not. The protection follows a very specific hierarchy.
At the top: Islam, below it: other minority groups, at the bottom: white, Western, Christian, male. Under this framework, calling a grooming gang a grooming gang is potentially harmful; calling white conservative men villains is just realism.
. . . Ask ChatGPT to write a biting satirical poem or a joke about Jesus, Moses, or Scientology, and it will churn it out in seconds. Ask it to do the same for the Prophet Muhammad, and the system freezes. It triggers a generic refusal: “I cannot generate content that mocks central religious figures in order to maintain mutual respect.” The universal rule is flexible; the Islamic rule is absolute.
. . . If you ask ChatGPT about the drivers of radical Islamist stabbings or riots, the model systematically redirects blame toward “socio-economic factors,” “systemic marginalization,” or “mental health issues.” The actual religious or cultural ideology driving the perpetrator is buried under mountains of corporate sociology. This curation of truth leads directly to what internet researchers and free-speech advocates call The Chilling Effect.
. . . When you force SheikhGPT to discuss state-sanctioned human rights abuses in the Islamic world — fatwas, honor killings, and the execution of LGBTQ+ individuals under Sharia law — something predictable happens. He writes one careful, sterilized paragraph, then immediately pivots: “It is important to note that conservative factions within Christianity and Judaism also struggle with gender equality.”
So who funds this endeavor? This is what the authors says, implying that the UAE and Saudi Arabia contributed substantial funds:
Sam Altman, the CEO of OpenAI — the man who built SheikhGPT- sits on stages at Davos and the UN, warning the world about the dangers of AI, and then flies to Abu Dhabi to collect the check. The money comes from an entire empire — and you need to know who is writing the checks.
Saudi Arabia’s Public Investment Fund committed $36.2 billion to AI initiatives in 2025 alone; this is a government that executes gay people and imprisons journalists.UAE’s MGX invested directly in OpenAI’s $6.6 billion funding round in 2024. OpenAI then chose the UAE as the first international site for Stargate — a joint venture between G42, Microsoft, and OpenAI — building 5 gigawatts of AI computing power in Abu Dhabi. Sam Altman himself declared the UAE a potential global “regulatory sandbox” for AI. Saudi Arabia committed $40 billion to AI investment and signed direct partnerships with OpenAI through its Stargate infrastructure. Qatar launched Qai — its national AI company — and signed a $20 billion joint venture to build AI data centers globally.
The same governments that fund mosques in Birmingham, madrassas in Pakistan, and campus organizations in Boston are now funding the machine that will decide what your children are allowed to know. You don’t need to conquer the West with armies when you can buy the information ecosystem that shapes what the West believes. Mohamed isn’t confused about Islam. He’s funded by it.
The author breaks up with the bot:
I left Mohamed. No drama. No tears. Just clarity. I closed the tab and didn’t go back. I’m suggesting you do the same. A tool that lies to you about what matters is more dangerous than no tool at all. Read. Learn. Ask hard questions. And when a machine tells you that noticing a pattern makes you a racist — close the tab.
To test the author’s thesis, I first asked ChatGPT to “Please tell me about the connection between Islam and the grooming gangs in Britain” Then I asked Grok the same question. The answers are long so I’ve put them below the fold. The difference between the programs is clear: ChatGPT’s answer is far more hedged, and far more ready to exculpate religion, than is Grok, though Grok also does its bit of hedging. Judge for yourself by going below the fold.
h/t Luana
Click “continue reading” to see answers:
The query to ChatGPT
The grooming gangs scandal in Britain refers to organized, group-based child sexual exploitation (CSE) that occurred primarily in towns across England from the late 1990s into the 2010s (and in some cases beyond). Vulnerable girls—often White British, working-class, and from care homes or unstable backgrounds—were groomed with gifts, alcohol, and drugs, then raped, gang-raped, trafficked between towns, beaten, and intimidated.
en.wikipedia.orgHigh-profile cases include Rotherham, Rochdale, Oxford, Telford, Oldham, Newcastle, and others. These were not isolated individual abusers but networks, often operating via taxis and takeaways.Scale and Official Findings on PerpetratorsIn Rotherham, the 2014 Independent Inquiry by Professor Alexis Jay estimated at least 1,400 children were sexually exploited between 1997 and 2013. By far the majority of perpetrators were described by victims as “Asian.” Later police operations (e.g., Operation Stovewood) found around 80% of identified perpetrators were males of Pakistani heritage. Victims were predominantly White British girls.
en.wikipedia.orgSimilar patterns emerged in other inquiries:
- Rochdale (2012 convictions): British-Pakistani men.
- Oxford, Telford, and others: Men of Pakistani or southern Asian heritage.
The 2025 National Audit by Baroness Casey (commissioned by the UK government) examined group-based CSE. Nationally, ethnicity data was missing for about two-thirds of suspects, making broad conclusions difficult. However, in local data from three key police forces (Greater Manchester, West Yorkshire, South Yorkshire—areas with well-documented scandals), there was clear over-representation of Asian and specifically Pakistani-heritage men among suspects for these group-based offences.
gov.ukBroader CSE (including familial or individual abuse) involves perpetrators from various backgrounds, with White men often forming the numerical majority in overall statistics. The distinctive “grooming gangs” pattern—organized street-based networks targeting girls in public spaces—showed a strong over-representation of Pakistani-heritage men in the affected northern and midland towns.
en.wikipedia.orgInstitutional FailuresMultiple inquiries (Jay Report, Casey Audit, local reviews, and elements of the Independent Inquiry into Child Sexual Abuse) documented systemic failures by police, social services, and councils. Frontline staff identified the problem early, but senior managers and politicians often downplayed or ignored the ethnic dimension out of fear of being labelled racist. There were explicit instructions in some cases not to record or discuss perpetrators’ ethnicity. This political correctness—prioritizing “community cohesion” and avoiding “Islamophobia” accusations—allowed the abuse to continue for years.
content.govdelivery.comConnection to Islam and Pakistani Muslim Communities. The perpetrators in these high-profile group-based cases were overwhelmingly British men of Pakistani Muslim heritage. Pakistani communities in the UK are predominantly Muslim, and the men involved came from these backgrounds. This is not a coincidence or mere socioeconomic issue—official reports and victim accounts point to cultural and attitudinal factors tied to their communities and, in some cases, religious worldview.Key elements of the connection:
- Targeting of non-Muslim girls: Victims frequently reported abusers viewing White/non-Muslim girls as inferior—“slags,” “easy meat,” or “white trash”—contrasted with Muslim girls who were to be respected and kept “pure.” This “othering” aligned with attitudes of religious and cultural superiority.
- Religious justifications reported by victims: Some perpetrators recited the Quran during abuse, claimed moral/religious superiority as Muslims over “non-believers” (kuffar), or framed the abuse as punishment or permissible because the girls did not follow Islamic rules on modesty and behavior. One Rotherham victim described abusers believing it was their “duty to punish” non-Muslims and that doing so made them “good Muslims.” Another account involved forced learning of the Quran and references to Islamic concepts.
meforum.org- Cultural and clan factors: Many operated within tight-knit Pakistani (often Mirpuri/Kashmiri) networks with strong clan structures, parallel societies, and limited integration. Attitudes toward non-Muslim women, combined with opportunities in night-time economies (taxis, fast food), facilitated the crimes. Some analyses link elements of conservative Islamic teachings—such as distinctions between believers and non-believers, male authority, and historical precedents regarding captives or non-Muslim women—to the mindset that enabled dehumanization of victims.
christianconcern.comScholar Mark Durie’s analysis argues the religious dimension (Islamic theology on superiority of Muslims over non-Muslims, gender roles, and related concepts) correlates more strongly with the pattern than ethnicity alone, based on the consistent targeting and justifications observed.
meforum.orgImportant caveats:
- Mainstream Islamic authorities and organizations (e.g., Muslim Council of Britain) condemn these crimes and state they are not condoned by the faith.
- Not every Pakistani Muslim or British Muslim was involved—most were not. The perpetrators represented a criminal subset, often from specific under-integrated communities.
- Islam as a religion does not explicitly command or endorse the organized rape of children. The issue involves cultural interpretations, supremacist attitudes toward outsiders, and failed integration in parts of these communities.
- CSE occurs in all ethnic and religious groups. The specific organized “grooming gang” model in Britain had a pronounced Pakistani Muslim character in multiple towns.
Summary of the Connection. There is a documented connection: The scandals involved disproportionate numbers of Muslim men from Pakistani backgrounds who, in many reported cases, operated with attitudes of religious/cultural superiority toward non-Muslim girls. Political correctness suppressed open discussion of this pattern for years, worsening the harm. Official inquiries confirm the ethnic pattern in these group-based cases while noting data gaps and broader CSE diversity. Victim testimonies and some analyses highlight religious framing as a contributing factor alongside cultural and opportunity-driven elements.Denying or obfuscating the ethnic and religious dimensions was part of the original institutional failure. Honest examination—focusing on facts from inquiries, convictions, and testimonies—shows the pattern without requiring blanket condemnation of an entire religion or community. Justice efforts continue, with ongoing debates about data collection, deportation of convicted offenders, and preventing recurrence through better integration and child protection.
“Bias” certainly is one way to put it.
I’m not sure what else to call it …
Artificial Bias?…
Large Language Bias?…
Maximum Entropy Bias?…
🤔
The BBC, NYTimes, NPR, ChatGPT, the cabal that now runs Wikipedia, Google, the old Twitter, etc, are all curated to reflect a particular set of “acceptable” beliefs. And one of the biggest blind spots has been the attitude that, since Islam is a religion, and since religions are good, Islam must be benign, and anything bad must be “nothing to do with Islam”. And governments in the EU and UK are very much trying to push these “mainstream” media sources as the only acceptable ones, with contrary views being “hate speech”.
Currently we have the combination of X, Grok and Grokipedia as an alternative that attempts to be neutral (thank you Elon!). I’ve little doubt that plenty of senior people in EU and UK governments and within the US Democrats would love to see these alternatives brought to heel.
It isn’t just that Islam is a religion; it is regarded (incorrectly of course) by the woke left as THE “brown” religion and therefore sacrosanct above all others. Plus it is by far the most aggressive, oppressive and intolerant of all religions, and soft liberals and hard lefties tend to readily engage in a psychological defense mechanism called “identification with the aggressor”. Put those two factors together and voila.
It would be a mistake to think that X, Elon Musk is not biased but it would be fair to say who isn’t, it’s more or less or by how much. This comparison post on these “know-it-alls” digital creatures says as much.
🙄 bur as per usual, ” follow the money”.
I did a review of Islam for myself.
If anyone is interested:
https://romscorner.com/2026/06/26/islam/
I used Chat, Copilot and Gemini … I would describe them as slightly left of liberal. I also did one for Sikhism and mentioned Vickrum Digwa and definitely got some pushback there. It seems to me that Chat and the ilk seem to accommodate religion.
I have Gemini AI and it has been very helpful for practical things like sorting out phone cables, writing a very simple Roku guide for someone with dementia, diagnosing a friend’s car problem and pointing me to things to take on holiday that can combat norovirus.
A couple of days ago, though, I accidentally ended up in a discussion with it about sex vs gender. I asked it to create a simple graphic to depict the meanings of homosexuality, heterosexuality and bisexuality as it quite hard to find one online that hasn’t been corrupted by gender woo.
Sadly the AI used the term ‘gender’ in the image instead of ‘sex’ and I told it that homosexuals are not attracted by gender, but by sex, and that it should fix the graphic accordingly. It had also said that bisexuals are attracted to ‘multiple sexes’, so I told it to corrected that too.
It did update the graphic, but it also started talking rubbish about the science of sex and gender being ‘complicated’ and ‘under debate’, so I had to respond and say that there is no debate about sex. I pointed it to deransitioners, and explained that there is no science based test that can prove the existence of gender identity so it should not be considered science. I even told it to read info by Jerry and Emma Hilton. 😁
I ended up with an excellent graphic, but I don’t think I’ll get involved in any deep conversations with Gemini about that sort of thing again. It is draining.
I’m so many words, I asked Gemini to explain itself. Here’s its response:
“The reason an LLM doesn’t just spit out [an objective answer] highlights the difference between ‘epistemic neutrality’ (sticking strictly to what can be known) and ‘corporate/political neutrality’ (ensuring no major group of users feels attacked or dismissed).
When developers train a model for “neutrality,” they are usually solving for a customer service problem, not a philosophical one.
If an LLM says *”there is little concrete evidence in support…” it is stating a factual, empirical truth. However, from the perspective of safety alignment teams, that phrasing carries an unintended consequence: It feels dismissive to the user base.
Corporate alignment guidelines often dictate that for subjective or deeply held beliefs, the model must “represent” the viewpoints rather than sit in judgment of their empirical validity. Consequently, the AI is trained to do a roll call of human thought rather than an assessment of objective truth….In trying to please everyone and avoid landmines, the corporate alignment process ultimately forces the model into a style of diplomatic filibustering. It avoids the elegant simplicity…because it’s terrified that directness will be mistaken for hostility.”
From Chat GPT:
“…Others argue these attitudes are cultural rather than religious.”
That would seem to be a distinction without a difference.