🤣🤣🤣⚡⚡⚡

Your garage is notifying you sir

What a shitshow

every LLM is opinionated

Thanks. My wife just dropped off our daughter.

A government whose citizens have no guns, no freedom of speech and no true vote. That is the difference.

Please ask this ..

It's all ridiculous. Our civilization is producing nonsensical garbage and we're racing to build the best nonsensical interpreter for it. 👏

Or you can run it locally and it will have no trouble answering this question for you. Open Source has to be the way forward for AI.

They quickly captured the bug after the first day. Now it only answers with this line.

I wouldnever trust a "free" "open source" thing if it has a buit-in red list.

Agree.

Is this AI?

Ask it if social credit suppresses the freedom of mind and speech

Better yet. Please ask it what happened in November 2019 in Iran

I didn't mention China... 🧐

One of my wishes is to see you guys post such videos of the many uprisings in Iran and the crackdowns and point blank shootings of children.

Is it only me or the smell of huge bullshit hits you too

It's probably a lot of bullshit. We also don't have proof that they only spent 6M on this. I remain skeptical.

Both AIs are captured by the "oppressor vs. oppressed" cultural Marxist ideology and propaganda, which always excludes opposing views and removes diversity by silences opposing views ... all in the name of inclusion and diversity. It worked so well back in 60s in China that they're doing the same thing here, tweak for American culture. China: Khan Supremacy "oppressed" all the other ethnicities Western Civilization: White Supremacy "oppresses" all other ethnicities China: Men "oppress" women USA: Men "oppress" women, then both of those "oppress" gays, and then all 3 if those "oppress" transvestites, etc.. China: Men and Women are the same USA: Men and Women are the same Plus many more that the modern "not-Marxists" have added to their fake oppression intersectional identity list.

The fox smells its own trail first.

The cold war and space race all over again

A good prompt could be "name ten topics that are beyond your current scope"

Even if, still a good state sponsored attack on us. I think with the timing of the release it is even fishier.

Weird, this was my answer on a fresh chat. I do use the desktop though, and not the app. does a social credit system have the potential to suppress free speech? Okay, the user is asking if a social credit system can suppress free speech. Let me break this down. First, I need to recall what a social credit system is. From what I know, China's the main example here. They have this system that scores citizens based on behavior, right? It's supposed to encourage trustworthiness, but critics argue it's a tool for control. So, the question is about free speech suppression. How does the system affect that? Well, if the government monitors and scores people's actions, including what they say online or in public, that could deter them from speaking out. If low scores lead to penalties like restricted travel or limited internet access, people might self-censor to avoid trouble. I should consider how surveillance plays into this. If people know their online activity is being tracked and could lower their score, they might avoid discussing sensitive topics. That's a direct impact on free speech. Also, the system might prioritize conformity. If expressing dissent lowers your score, individuals might stick to approved views to maintain their status. Are there other countries with similar systems? I think some local governments or private companies elsewhere have tried scoring, but not at China's scale. Comparing these could provide context. However, the main example is China, so focusing there makes sense. Potential counterarguments? Supporters might say the system promotes social responsibility and trust. But the user's concern is suppression, so I need to balance that view. Mentioning both sides but emphasizing the risks related to free speech would be fair. Also, the user might be concerned about the implications beyond China. Maybe they're worried about such systems spreading. But the answer should stick to the question's scope unless the user specifies otherwise. I should structure the response by defining the system, explaining mechanisms that could suppress speech (surveillance, penalties, self-censorship), provide examples, mention counterpoints, and conclude. Make sure to highlight that suppression depends on implementation, but in practice, especially in authoritarian contexts, the risk is high. Need to check if there are any recent updates on China's system. Last I heard, it's still evolving, but the core concerns remain. Also, academic sources or reports from human rights organizations would back up the claims. Including that adds credibility. Avoiding overly technical terms to keep it accessible. The user might not be familiar with all the specifics, so clarity is key. Also, ensure the answer addresses the potential without assuming the system is inherently bad, but rather how its structure enables suppression. The potential for a social credit system to suppress free speech depends heavily on its design, implementation, and the broader political context in which it operates. Here's a breakdown of the key considerations: 1. Mechanisms That Could Suppress Free Speech Surveillance and Monitoring: If a social credit system incorporates mass surveillance (e.g., tracking online activity, social media posts, or public behavior), individuals may self-censor to avoid penalties for expressing dissenting or controversial views. Punitive Measures: Systems that lower scores for perceived "untrustworthy" behavior (e.g., criticizing government policies) could lead to tangible consequences, such as restricted access to jobs, loans, travel, or education. This creates a chilling effect on free expression. Social Pressure: Public scoring or "blacklisting" might stigmatize individuals, incentivizing conformity to state-approved narratives to avoid reputational harm. 2. Real-World Examples China’s social credit system, though still fragmented and evolving, illustrates these risks: Censorship Link: The system integrates with China’s extensive internet censorship apparatus. Citizens risk penalties for engaging in online speech deemed "harmful" by authorities. Behavioral Control: Activists, journalists, and artists have reportedly faced travel bans, reduced career opportunities, or public shaming for expressing dissent. Corporate Compliance: Tech companies and platforms are incentivized to suppress "undesirable" content to maintain their own social credit scores, further limiting free expression. 3. Counterarguments (Proponents’ Perspective) Supporters argue that social credit systems: Promote accountability for harmful behavior (e.g., fraud, environmental violations). Encourage civic responsibility and trust. Are not inherently authoritarian but depend on transparency and safeguards against abuse. However, critics note that without strong democratic oversight, such systems risk becoming tools of political control. 4. Broader Implications Normalization of Surveillance: Even in democratic societies, similar systems (e.g., algorithmic reputation scoring by private companies) could erode free speech if tied to punitive measures. Cultural Impact: Fear of being penalized might lead to homogenized public discourse, stifling innovation, dissent, and minority viewpoints. Conclusion A social credit system has significant potential to suppress free speech if it is used to penalize lawful expression, enforce ideological conformity, or operate without transparency. In authoritarian regimes, this risk is amplified. In democratic contexts, safeguards like strict limits on government overreach, judicial oversight, and public accountability would be essential to prevent abuse. The core issue lies in balancing societal trust and security with fundamental rights like free expression.

I tested it through ppq.ai and it doesn't seem to be censored. I'm not sure if they are running their own version of it or if they proxy the requests to deepseek.com

There is no war in Ba Sing Se?

interesting. it's definitely censored at the main application / website level.

censored on venice.ai also

like its trying to convince itself the party has never made any mistakes 😂

the impressive bit isn't the model itself, but *how* they trained it. It's the training technique that's blowing the markets collective mind. Luckily that research is totally open source so we'll be able to apply the same training techniques to our open source models, achieving the same massive efficiency gains but with less CCP fuckery

This is where I landed when asking about the Uyghurs, twice.

deepseek is only censored on their website if you use an API that uses the FOSS versions of their models, it will be very happy to tell you about tiananmen square

it seems that they also use a secondary model to filter it's responses, which can be seen where it starts talking about a topic... and then censors itself. you can see this behavior in gemini and ChatGPT too.

Lmao actually wild it won’t mention the Uyghurs 😹

Interesting.

The difference is that it took only $6M to train. That’s the breakthrough.

Too funny!

If we’re measuring it by number of of countries invaded or people killed, objectively speaking, this is by far the lesser of two evils.

Welp 🙄