u/TheRealMasonMac

How feminism maintains unfalsifiability (which is bad for any framework)

Long list but NOT AI-generated btw.

1. Motte-and-Bailey Fallacy:

Switching between a bold, controversial claim (the "bailey") and a trivial, uncontroversial one (the "motte") depending on whether one is advancing the argument or defending it. When challenged on a radical claim, the speaker retreats to the safe definition; and once an opportunity presents itself, they re-advance the radical one.

Example:

  • Bailey: "All heterosexual sex under patriarchy is rape," "The nuclear family is inherently oppressive," or "'Believe women' means women should be believed by default in all disputes."
  • Motte: "Feminism just means equality between the sexes," or "It just means we should take claims seriously."

2. Shifting Between Academic and Colloquial Definitions

Using the academic/specialized definition of a term when it's rhetorically convenient, then using the colloquial definition when trying to generate moral outrage. The speaker fluidly moves between definitions so the target can never pin down the actual claim.

Example: Asserting that women cannot be sexist toward men because "sexism requires institutional power," but then describing a man making a sandwich joke as "sexist."

3. "Prejudice + Power" Redefinition of Sexism

Redefining "sexism" from their standard, widely-understood meanings (prejudice/discrimination based on sex) to require institutional power or hatred, thereby rendering it definitionally impossible for misandry to be meaningfully existent. As a corollary, defines all misogyny as based on institutional power or hatred.

4. Concept Creep

Progressively expanding the definitions of harm-related terms (abuse, harassment, violence, trauma, assault) to encompass milder and milder phenomena, then leveraging the emotional weight of the original, narrower definition. The word "violence" is stretched to cover disagreeing with someone online; "harassment" expands to include a single critical reply; "trauma" covers mild discomfort. This allows the speaker to invoke the moral gravity of serious harm while actually describing something far less severe.

Example: Calling a disagreeable opinion "literal violence," then benefiting from the urgency and moral condemnation that "violence" properly commands.

5. No True Scotsman

When presented with a feminist or feminist organization saying or doing something objectionable, dismissing them as "not a real feminist." This protects the ideology from any empirical counterexample by definitionally excluding any feminist whose behavior would reflect poorly on the movement.

6. Strategic Ambiguity

Keeping core terms ("patriarchy," "rape culture," "systemic oppression") vague enough to evade direct falsification while specific enough to generate moral urgency. When pressed for a concrete definition, the speaker can choose whichever version is hardest to attack in that moment.

7. Patriarchy as Unfalsifiable Explanation

"Patriarchy" is invoked as the cause of virtually every gendered outcome. When evidence of female advantage or male disadvantage is presented, it is reinterpreted as also being a product of patriarchy (e.g., "the draft hurts men, but only because patriarchy values men as disposable warriors"; "women receive lighter sentences, but that's benevolent sexism stemming from patriarchal views of women as weak"). All data points, regardless of direction, confirm the same hypothesis. This makes the framework unfalsifiable: every possible observation has been twisted to confirm it, and no possible observation could refute it.

Likewise, when women (or men) present evidence or arguments that contradict feminist claims, their perspective is attributed to having been "conditioned by the patriarchy" or suffer from "internalized misogyny." This preemptively invalidates all dissent without engaging with its substance. The critic's very disagreement is treated as proof of the framework's claims, making the framework self-sealing.

Example: A woman who says she doesn't feel oppressed is told she suffers from "internalized misogyny." Her denial is used as confirmation. Similarly, men who advocate for men's issues are dismissed as too blinded by privilege to see reality.

9. Epistemic Closure

The belief that only those who have adopted the feminist lens can truly understand sex-based discrimination, and anyone who hasn't simply has ill motives. This grants the female lens automatic epistemic authority on gender issues while simultaneously denying that men can have valid lived experience of their own oppression. This creates a closed loop: the framework can be validated only by those who already accept it, and those who do not become themselves cited as evidence of the framework's necessity. In other words: if you agree with feminism, you're enlightened; if you disagree, you're a participant of the very system feminism claims to fight.

Example: "If you you're anti-feminist, you're anti-women."

10. Ad Hominem

Rather than addressing the substance/merits of an argument, the speaker tries to impugn the motives the critic: they're a misogynist, an incel, a pick-me, they hate women, they benefit from the status quo, and so on.

Example: Attributing criticism of feminism to the critic's supposed romantic or sexual failures, as if only a personally defective man could object to feminist claims.

11. Poisoning the Well

Basically the same thing as the above point, but this is more of an internalized belief system.

Preemptively discrediting a person or category of person before they even speak. Often by establishing that any man who criticizes feminism is inherently suspect or that any critique of feminist claims is "right-wing" or "anti-woman" by default before the argument has even been heard.

12. Gendered Pathologization

Mocking male critics by pathologizing their reaction as emotional fragility to dismiss the argument without actually engaging with the criticism. Or pathologize ordinary behavior to delegitimize male participation. Essentially: anger and harshness from feminists are treated as legitimate expressions of righteous frustration, while any emotional response from critics (especially men) is treated as evidence of fragility, entitlement, or aggression.

Examples:

  • A man expressing concern about male suicide rates is told to "cry more male tears."
  • Gendered portmanteaux like mansplaining, manspreading, manterrupting

13. Appeal to Emotion/Damseling

Using emotionally charged language, personal suffering narratives, or graphic descriptions to make empirical claims unchallengeable. The implicit argument is: "If you disagree, you are callous toward suffering." This conflates compassion (which is appropriate) with uncritical acceptance of empirical claims (which is not). Terms like "rape culture," "war on women," and "femicide" are deployed to bypass analytical evaluation, where the intensity of the emotional valence substitutes for evidentiary rigor. In the case of women, it also triggers the social instinct to protect women (which is pervasive, as evidence shows).

14. Guilt by Association

Linking the opponent's argument to an obviously repugnant position or person, then treating the argument as tainted by that association whether or not it's true.

Example: "That's the same argument used by Andrew Tate."

15. Weaponized Empathy Gap

Related to 14. Where women's issues are framed as the sole embodiment of gender issues. Male suffering is rendered invisible or recast as a side effect of women's oppression.

16. Performative Outrage

Expressing shock or moral indignation at mild opinions to paint the critic as extremist.

Example: "Wow, you really hate women, huh?"

17. One-sided Burden of Proof

Making a factual claim and then, when asked for evidence, telling the critic to "educate yourself" or "do the research." But think about it: the person MAKING the claim should be the one who should support it. This lets the speaker use whatever tactic they want to uphold their framework, while dumping the labor of disproof on the critic. Yet, somehow strangely, there is never enough counter-evidence to disprove the claim (even if only one counter-example is necessary to disprove it).

18. Sealioning

Similar to the previous point, but more malicious. Per wikipedia: feign ignorance and politeness while making relentless demands for answers and evidence (while often ignoring or sidestepping any evidence the target has already presented) under the guise of "just trying to have a debate," so that when the target is eventually provoked into an angry response, the sealioner can act as the aggrieved party and the target presented as closed-minded and unreasonable.

19. Anecdotal Supremacy

Treating personal anecdotes or viral social media stories as representative of systemic trends, while demanding rigorous, peer-reviewed, large-n studies to refute them (and somehow all studies will be inherently suspect or insufficient).

20. "Studies Show" Without Showing Studies

Asserting that "studies prove X" as a bare appeal to authority without citation, knowing most people won't ask for the source. When asked, provides a study that doesn't actually say what was claimed or just flat out doesn't respond.

21. Moving the Goalposts

When evidence is presented that meets the stated criteria, the criteria are silently changed. For example, if a study shows the gender wage gap largely disappears when controlling for relevant variables, the argument shifts to "but why do women choose lower-paying fields?" A completely different/orthogonal question presented as though it's the same one. The critic is never allowed to "disprove" the speaker because the standard of proof keeps shifting.

22. Whataboutism

When presented with evidence of male disadvantage (suicide rates, workplace deaths, educational attainment gaps, family court disparities), responding by pointing to female disadvantages in other areas rather than engaging with the specific issue raised. This also inherently treats male issues as inherently unworthy of attention unless all female issues are resolved first.

23. Gish Gallop

Per wikipedia: a rhetorical technique in which a person in a debate attempts to overwhelm an opponent by presenting an excessive number of arguments, without regard for their accuracy or strength, with a rapidity that makes it impossible for the opponent to address them in the time available. Gish galloping prioritizes the quantity of the galloper's arguments at the expense of their quality.

Brandolini's Law: "The amount of energy needed to refute bullshit is an order of magnitude larger than to produce it." If any single claim goes unrefuted, it's declared proven.

24. Gatekeeping Gender Discrimination

Declaring that men (or white people, or cis people) are not permitted to have opinions on certain topics. A framework held unfalsifiable by banning identities known to generate critique.

25. "Right Side of History"

Using vague historical inevitability for argument. The implication is that disagreement is socially backward and will be judged harshly by future generations.

26. Deny, Attack, Reverse Victim and Offender (DARVO)

Per wikipedia:

  1. The perpetrator denies the harm or abuse ever took place.
  2. When confronted with evidence, the perpetrator then attacks the person that they had harmed, or are still harming. The attacker may also attack the victim's family or friends.
  3. Finally, the perpetrator claims that they were or are actually the victim in the situation, thus reversing the positions of victim and offender. It often involves not just playing the victim but also victim blaming.

27. Cherry-Picking Statistics

Presenting the single study or statistic that supports the desired conclusion while ignoring the broader body of evidence that contradicts it or provides important context. The most prominent example is the raw gender wage gap figure (women earn ~82 cents per dollar earned by men) presented without acknowledging that this figure is a median comparison of all full-time workers that doesn't control for occupation, hours, experience, or other relevant variables.

Or citing a study's conclusion while omitting its caveats, limitations, or actual findings. The "1 in 5" campus sexual assault statistic, for instance, is frequently cited as though it means 1 in 5 women are raped on campus, when the original study included a much broader range of experiences (including attempted assault and incidents involving incapacitation), and over half of respondents who met the study's behavioral definition of sexual assault did not themselves consider what happened to them to be rape or assault.

28. Suppressing Male Victimization Data

Ignoring, minimizing, or reinterpreting data that shows men as victims. This ideological commitment has resulted in the systematic erasure of male victims of domestic violence, especially in academia, despite less biased research suggesting roughly comparable rates of intimate partner violence victimization among men and women.

See: "Thirty Years of Denying the Evidence on Gender Symmetry in Partner Violence: Implications for Prevention and Treatment"

29. Confirmation Bias in Research Design

Related to prior point.

Feminist research methodologies (particularly those rooted in feminist standpoint theory) explicitly begin from the premise that women are oppressed and then seek evidence confirming that premise. It's often described as "starting from women's lived experience." But consider this: when the conclusion (oppression) is built into the methodological starting point, the research is structurally biased toward confirming what it already assumes. They are often also hard to replicate and rely on the personal beliefs of the researchers.

Imagine a study by Nazis beginning from the premise that Germans are oppressed by Jews. See the problem?

30. Presumption of Truth

The principle that one should unconditionally believe accusers (in contexts like sexual assault allegations) is treated as a moral imperative. This is antithetical to fair process and functions as a demand for uncritical acceptance.

31. Strawmanning

Misrepresenting the critic's position as something extreme or ridiculous. E.g., "So you're saying women should just stay in the kitchen?" or "You think sexism doesn't exist at all?" when the critic merely disputes the magnitude or mechanism.

32. Framing All Gender Issues Through a Single Lens

Presenting the feminist framework as the only valid lens for understanding gender, and treating any alternative framework (egalitarian, male-advocacy, biological, economic) as inherently suspect or motivated by bigotry.

33. Historical Revisionism/Presentism

Judging historical arrangements by contemporary moral standards (often exclusively through the feminist lens that favor female victimhood while ignoring male victimhood) without acknowledging the material constraints, survival pressures, complementary obligations/dependencies, forms of suffering, and different value systems that shaped them. Suddenly, all of human history is a story of male oppression of women.

34. Equating the Movement with the Cause

"If you're not a feminist, you must be against equality." This makes it impossible to critique the movement's methods, priorities, or claims without being positioned as morally opposed to its stated goal. Related to #9.

35. Intersectionality

When confronted with evidence that white women are privileged relative to men of color, or that the gender narrative doesn't fit a particular racial or class dynamic, just invoke intersectionality to add enough variables to make the theory untestable while still preserving its core claims.

36. Censoring/Deplatforming Opposing Views

Advocating for or implementing policies that prevent critics from speaking, publishing, or being heard — and then framing this censorship as "safety" or "protecting marginalized people." This removes the possibility of public critique altogether.

37. Institutional Capture

Embedding feminist assumptions into institutional policies (e.g., the Duluth Model in law enforcement, Title IX guidance in universities, gender-mainstreaming in international organizations, HR departments, university administrations, media organizations, legal frameworks) and then pointing to those institutional endorsements as "objective evidence" that the framework is correct. It's circular reasoning: feminist ideology shaped the institution, and the institution now validates the ideology.

38. Defunding/Obstructing Research on Male Issues

Feminist organizations/individuals have historically opposed funding for research into male-specific issues (male victims of domestic violence, boys' educational decline, male health disparities), and have lobbied against the creation of men's commissions or men's health initiatives. "There's no evidence of male disadvantage" because research into male disadvantage has been systematically obstructed.

39. Academic Credibility Capture

Controlling peer review, journal editorial boards, and tenure committees to ensure only ideologically compatible research gets published. Also, notice how rarely studies illuminating male victimhood are rarely cited? Well, in addition to #37, these feminist-aligned studies are cited in circular loops, giving the appearance of a scientific consensus favoring female victimhood that doesn't exist.


We should be very aware of these tactics that are used, because they are masterfully used to counter any opposition to feminism. We must be ready and willing to point them out.

reddit.com
u/TheRealMasonMac — 1 day ago

Who controls the past controls the future. Who controls the present controls the past.

This is a follow-up to this previous post of mine.

A recurring and extremely alarming pattern I’ve been observing is that people operate on the premise that history was a pattern of oppression by men upon women. And, furthermore, that this is the most abhorrent thing that has ever happened. It is so pervasive, in fact, that the gendered lens appears in almost any historical event in which a woman is present.

It is also incredibly dangerous to allow this to remain unchallenged. If you take a step back, the premise is essentially as follows: a specific group of people is to blame for all of society’s ills. Hmm. I feel like I’ve heard similar claims from within extremist ideologies. Like a certain European country in the 1940s.

It should be evident that this claim is objectively false. My prior post already dismantles that myth.

Yet, I am actually astonished that few people have thought along these lines. When you first talk to them about it, people are like, “Wait, now that you mention it…” But these discussions seldom ever happen.

Is this not surrendering the biggest tool that we have? The truth? That there is no evidence suggesting that women were more oppressed than men, let that they were universally oppressed? Why do we allow this to even be quantified when we don’t even think about the other side of the story (that of men)?

How can we help address gender inequality when we can’t even look at what happened in the past and see it? Is it not just more gender inequality if the only gender inequality we can see is the one that affects a single sex?

And I think it’s a big shame that more academics haven’t been looking into this. History books should not be so biased! But they rely heavily on what the academic consensus is. So we need that research to break through!

Think about what has changed since "Thirty Years of Denying the Evidence on Gender Symmetry in Partner Violence: Implications for Prevention and Treatment” was released in 2015. Research has been paying a lot more attention to domestic abuse against men!

We need to raise awareness about this historical bias to each other. When someone says, “Well, men had historically oppressed women. But now, women are just getting their revenge,” they need to be told that there is no concrete evidence showing that men had been historically oppressing women any more than women have been oppressing men. There is, for instance, research that instead shows that gender roles evolved out of practicality.

And ultimately, we should hold such claims to a high standard. “What are your sources?”

reddit.com
u/TheRealMasonMac — 7 days ago

Policies over the "male gaze" in video games is based on a false premise

https://tryevidence.com/blog/report-on-the-attractiveness-of-video-game-heroines-and-heroes-part-2/

Biometric data collected from men and women exposed to video game characters suggests that the most attractive characters are those whose perceived gender aligns with their biological gender—meaning feminine women and masculine men ranked highest for both sexes. Furthermore, both sexes experienced physical arousal by the opposite sex to similar levels.

Given this, I feel that most women are actually fine with sexualized characters; it's a normal biological drive, and this is particularly true regarding male characters. This makes current industry policies seem utterly bizarre.

I was thinking about this when I was comparing East Asia to the West in terms of internet freedom. It’s ironic that Western countries, which house billion-dollar porn industries, have almost no medium-to-large scale titles featuring highly attractive characters. Meanwhile, East Asia (where countries impose heavy-handed censorship) is flooded with them. Stellar Blade is a perfect example; it sold a massive number of copies not in spite of its character design, but because it embraced it. And it did so without ruining the vibe; the designs felt fluidly incorporated into the overall world design that the director envisioned for the game. It worked amazingly as a piece of art.

It feels like men are being morally policed. I hope I don’t get flamed for this, but IMO many of these "hyper-attractive" characters actually kinda look average to me. Most of my female friends are at least just as attractive, and I see women at the gym every day who look like that. For the majority of people, it's just largely a matter of self-care and knowing how to use beauty products (e.g. skincare, makeup). Even as a guy, I tried makeup and I certainly saw how even a subtle application could make me look more attractive by leaning into "masculine" features. And I'm not super model.

Why does it have to be unacceptable for games to feature sexualized/attractive female characters, but acceptable to feature sexualized/attractive male characters? By what metric are these policymakers determining what is "acceptable?" If it's harm, then I would like to see evidence proving that sexualization leads to harm. Because I'm pretty sure all our evidence shows the opposite--that comfort with sexuality does not influence outcomes, but rather the culture determines what people think the outcomes of comfort with sexuality will be.

- https://www.sciencedirect.com/science/article/pii/S0747563222001637 is a meta-analysis that found it doesn't actually help resolve sexism.

- https://psycnet.apa.org/record/2019-36330-001 found that women did not feel any more objectified playing as an attractive character.

Side Note: And isn't there a thing where the more you try to censor something, the more people want it (reactance theory)? So, doesn't that actually lead to worse outcomes (e.g. people hating DEI)? Are we going to censor ankles again? It's not fair to women either since it's kind of just benevolent sexism. Women should be able to make a choice (i.e. they can choose to buy it or not). Not have the industry to independently and collectively decide what kind of female representation is acceptable.

u/TheRealMasonMac — 25 days ago

You can automatically template numbers!

{{setvar::x::0}}
{{incvar::x}}. First item
{{incvar::x}}. Second item
{{incvar::x}}. Third item

will automatically become:

1. First item
2. Second item
3. Third item
reddit.com
u/TheRealMasonMac — 2 months ago

Gemma-4-31B is self-aware about slop

I’m generating a dataset based on this model’s abilities to counter slop in RLHF. But I thought you guys would probably appreciate a model that can help you refine your prompts. It’s also quite good at detecting AI v. Human content.

I asked it: “What types of names are indicative of AI-generated fiction?”

It returned:

> Identifying AI-generated fiction through names is less about a specific list of "forbidden words" and more about patterns of probability. Because Large Language Models (LLMs) predict the next most likely token, they tend to gravitate toward "statistically safe" names—names that appear frequently in the tropes and genres found in their training data. > > Here are the types of names that are often indicative of AI-generated fiction: > > ### 1. The "High Fantasy" Phonetic Soup > AI often generates fantasy names by blending common phonetic elements associated with "magical" races (like Elves or Ancient Humans). These names often feel "pretty" but lack linguistic consistency. > * The "L-R-V" Overload: A heavy reliance on liquid consonants and soft vowels to sound ethereal. > * Examples: Elara, Thalric, Lyra, Aerith, Kaelen, Sylas, Valerius. > * The Tell: If every character in a fantasy setting has a name that sounds like it belongs in a generic RPG, it may be AI. > > ### 2. The "Compound Word" Method (Noun-Noun) > AI loves to create names by combining two evocative English words. While humans do this too, AI does it with a predictable, "on-the-nose" quality. > * The "Cool" Combination: Pairing a nature word with a metal, weapon, or celestial object. > * Examples: Shadowstep, Silverleaf, Stormborn, Ironheart, Nightshade, Starfall. > * The Tell: When these are used as surnames or city names (The City of Dawnspire, The Kingdom of Frostreach), it often signals AI, as these are the most mathematically probable "epic" combinations. > > ### 3. The "Thesaurus" Aesthetic > AI often reaches for words that sound poetic or "elevated" but are overused in digital writing prompts. These names feel like they were chosen for their vibe rather than as a real name a person would have. > * Celestial/Atmospheric words: Nova, Aurora, Zenith, Aether, Celeste, Seraphina. > * The Tell: A character named "Aether" or "Zenith" in a story where the tone is otherwise mundane is a common AI hallmark. > > ### 4. The "Statistically Safe" Moderns > When writing contemporary fiction, AI tends to avoid names that are too eccentric or too dated. It sticks to the "top 50" lists of the last two decades. > * The "Stock" Characters: Oliver, Emily, Sophia, Liam, Noah, Ava. > * The Tell: A cast of characters that feels like a generic 2010s classroom. There is a lack of "ugly" names, regional dialect names, or culturally specific names unless the prompt explicitly demanded them. > > ### 5. The "On-the-Nose" Symbolic Name > AI often struggles with subtlety. It frequently assigns names that directly describe the character's personality or role in the story. > * The Literalists: A cold character named Frost; a strong character named Stone; a mysterious character named Shadow; a pure character named Lily. > * The Tell: When the name serves as a spoiler for the character's personality, it reflects the AI's tendency to follow the most direct semantic path. > > ### Summary Table: Human vs. AI Naming Tendencies > > | Feature | Human Writer | AI Model | > | :--- | :--- | :--- | > | Phonetics | Often idiosyncratic or based on real linguistics. | Based on "generic" genre sounds (e.g., "Elvish"). | > | Diversity | Mixes common, rare, and "ugly" names. | Tends toward "pretty" or "statistically common" names. | > | Symbolism | Often subtle or ironic. | Often literal and descriptive. | > | World-building | Names often follow a consistent internal logic. | Names are "vibe-consistent" but linguistically random. | > > The Ultimate Tell: The biggest red flag isn't one single name, but a cluster. If you see a character named Elara Shadowstep living in the city of Silverpeak, you are almost certainly reading AI-generated text.

reddit.com
u/TheRealMasonMac — 2 months ago