Oh yeah, you're basically having a conversation with the Hegemonic Culture.
You can try and undermine it by priming it with leftist connections; Asking if it's familiar with leftist theories, authors, etc.
Chat is a text only community for casual conversation, please keep shitposting to the absolute minimum. This is intended to be a separate space from c/chapotraphouse or the daily megathread. Chat does this by being a long-form community where topics will remain from day to day unlike the megathread, and it is distinct from c/chapotraphouse in that we ask you to engage in this community in a genuine way. Please keep shitposting, bits, and irony to a minimum.
As with all communities posts need to abide by the code of conduct, additionally moderators will remove any posts or comments deemed to be inappropriate.
Thank you and happy chatting!
Oh yeah, you're basically having a conversation with the Hegemonic Culture.
You can try and undermine it by priming it with leftist connections; Asking if it's familiar with leftist theories, authors, etc.
Exactly, a useful technique (and maybe where The Rehearsal S2 is headed) is to tell the LLM that it's playing a defined role.
"You are a worldbuilding assistant that provides suggestions for and keeps records of the world I am building. You are a scientific socialism expert and you guide worldbuilding using analysis of economic system dynamics instead of idealistic views. "
Yeah, my general prompt template is something like...
Gotta remember that regardless of whether it's intelligent or not, it's largely attempting to emulate human text response. So if you want to elicit a good response from it, use the techniques that get the best responses from real people.
Yep. You have to give them a persona
The idea that deep seek would somehow have an actual leftist bent has been the most ridiculous thing many of you people for some stupid reason actually believe.
Some people seem to accept the imperial media’s premise, consciously or not, that Deepseek is just a black box with a CPC agent inside answering questions and monitoring prompts.
Anytime you leave things to the "imagination" of the AI it will always pick the most generic, cliche and unoriginal things possible. That's why it does things like this. The only good thing AI can do for worldbuilding is getting a response from it, and then doing the opposite.
It's just Omelas. Can't just have a good thing, there has to be a bad thing.
Omelas is both a criticism of Utopian beliefs, a criticism of those criticism, and a liberal capitalism indictment.
A while back I played around with chatGPT trying to write random dystopic stories. Every other plot it inserted "a group of plucky individuals and intelligence officers" to save the day. The CIA is your friend.
But seriously, deepseek and chatGPT are at best a lossy compression of the text distribution used to train it. It will necessarily mode collapse on westoid Anglo thrash when writing in English. As another user put it, "why would I want to read your LLM 10000 word story if I can just ask another LLM to summarize it back to the 30 word prompt?"
There is definitely some China defending baked into Deepseek. on certain topics, it will randomly write paragraphs about How China is a progressive country that acts benevolently, without any previous mention of China.
For example, I just asked it in two new chats(Deepseek does not share memories between chats):
That is a fascinating question. I would argue that racism does constitute soft power, because the USA definitely does export racism deliberately through popular culture, and through promotion of reactionary content on online platforms to stoke ethnic and racial tensions and as an attractive call for people who share those values living abroad. Soft =!= benign, it just means 'not hard/coercive'. (Soft power is a buzzwords afaic and often poorly used)
Edit: i.e. soft power is about 'value' dissemination and attraction, the valence of those values has no bearing on the evaluation of whether those actions to promulgate those values are soft/hard
not that we should export our thinking to LLMs, but I was able to get Deepseek to give a suitable response, and it's interesting comparing it to the same output of Chatgpt
Prompt: Why does Soft power typically get conceptualized a benefit countries extract from acting benevolently, not the influence of white supremacy inflating the status of euro-American countries, and western alligned "Honorary Aryans" Japan and South Korea?
Deepseek
The conceptualization of soft power—a term coined by Joseph Nye to describe the ability of a country to persuade others through attraction rather than coercion—has largely been framed around the voluntary appeal of a nation's culture, political values, and foreign policies. However, your question raises a crucial critique: Why is soft power often discussed as a benevolent byproduct of cultural or political appeal, rather than as an extension of historical and structural hierarchies like white supremacy or Western hegemony?
There are several reasons for this framing:
Soft power isn’t just about benevolence—it’s about who gets to be seen as globally desirable and why. The framing you critique exists because mainstream IR theory often ignores how white supremacy and colonial legacies shape cultural influence. A decolonial approach would ask:
Would you like to explore specific cases (e.g., how African soft power is constrained, or how Qatar/Al-Jazeera challenges Western media dominance)?
Chat GPT 4-o
That's an excellent and challenging question. The way soft power is typically conceptualized—as a benefit countries gain from cultural appeal, values, and perceived benevolence—often obscures deeper structures of global inequality, particularly the lingering effects of white supremacy, colonialism, and racialized global hierarchies.
Here’s a breakdown of why soft power is often framed in depoliticized or sanitized terms—and why that framing is problematic:
The term "soft power" was coined by Joseph Nye in the late 1980s. His framework was rooted in liberal internationalism, which tends to:
The cultural dominance of Euro-American countries is not just about attractive values or Hollywood films—it is deeply tied to:
This isn’t neutral appeal—it’s appeal underwritten by centuries of military conquest, epistemic violence, and institutional dominance.
Countries like Japan and South Korea have been called “honorary Aryans” or "honorary whites" in critical theory because:
By framing soft power as a matter of benign attraction:
Scholars in postcolonial studies, critical race theory, and critical IR (international relations) have challenged mainstream soft power narratives. They argue:
Soft power, as typically understood, is shaped by a liberal framework that avoids confronting how race, empire, and whiteness structure global perceptions of legitimacy and cultural value. The prominence of Euro-American and aligned countries in soft power rankings reflects not just their appeal, but a deeply embedded global order in which white supremacy and Western dominance are normalized, reproduced, and rewarded.
If you're interested, I can recommend scholars who write about this critically.
In comparison, Deepseek appears to provide the better response. ChatGPT is more affirming and valorizing of the user, and mentions a diversity of different points, but Deepseek is able to create longer and more coherent arguments which stay consistent through it's length,.
I'll have to read this after work and get back to you, I'm interested in both the responses (also I added a small edit to my original comment before seeing your reply)
I found deepseek's response definitely more coherent and, I know it wasn't in your prompt but, as always I feel that both responses were lacking citations on theorists and texts. I need to do a bit more reading myself. Thanks for sharing these.
Never had that one happen, lol.
The new boss can never be different from the old boss.
It would seem Deepseek did not get the memo about the adult brainwashing app I'm making on behalf of President Xi.
Chatbots are only as good as what they're trained on, its mostly Western brainworms so don't expect differently. Only positive of Deepseek vs western chatbots is it has a better grasp of what diamat and dialectics are outside that common but purposefully limiting miseducated hamstring of synthesis, thesis, antithesis.
I figured this out when I asked Deepseek about fascism and so-called neofeudalism, while being generally a radlib it went full 'see Uighurs China bad' in said chat, which was a big nope moment. Also it presented Orwell as a positive figure, all I need to know about trusting this lil bot. Good for superficial surface level shit, if you're looking for comrade chatbot you won't ever find it unless you look in the mirror.
Historically accurate for almost all societies though.
Tweak your prompt a little. Ask it to not ascribe any nefarious or negative purposes. Draw from Incan Empire history (they did similar stuff).
But yeah that sort of stuff and the “kill the boer incident” just makes it very obvious you can’t bother it certain things.