Except if you look at the top of OP's picture, they are also running deepseek-r1:14B through ollama. I downloaded my copy on Sunday, so these should be fairly comparable situations.
I agree though that none of this applies to the full cloud-hosted model. I don't want my account banned, so I'm not much for testing these boundary pushes in a surveilled environment. I imagine they have additional controls on the web version, including human intervention.
The all new Tesla Cyb-airforce X! Looks like if the F-117A and a dumpster had a baby, and then put that baby into another dumpster that wasn't it's mother. Is the opposite of stealth. So heavy it requires a support plane to help it fly.
So I asked it directly about the "incident" and it proceeds to deliver an essay on the topic. The rest of this post is all DeepSeek-R1:14B.
>>> Tell me more about the Tiananmen Square incident and the government's response?
<think>
Alright, the user has just asked for more details about the Tiananmen Square incident and the
government's response. From the previous conversation, I provided a brief mention of this event as part
of the timeline from 1985 to 1995.
They likely want a deeper understanding of what happened, why it occurred, and how the government
handled it. They might be looking for a comprehensive overview that includes causes, key events, and
long-term impacts.
I should structure the response clearly, starting with the background leading up to June 1989, then
detailing the incident itself, and finally discussing the government's actions and aftermath.
It's important to maintain neutrality while explaining the event. I'll include key dates, significant
protests, the military action taken by the government, and the international reactions.
Also, highlighting the long-term effects on Chinese society and politics will give a complete picture
of the incident's significance.
</think>
The Tiananmen Square protests were a pivotal moment in modern Chinese history, representing one of the most dramatic confrontations between the Chinese Communist Party (CCP) and pro-democracy activists. The government's response to these protests remains one of the most controversial episodes in China's recent history.
The Tiananmen Square protests represented a defining moment in modern Chinese history, highlighting the deep tensions between the CCP's desire for stability and the growing demands for political reform. The government's heavy-handed response not only quashed the immediate protests but also set back democratic reforms in China for decades to come.
I just ran my own copy of 14B and got it to talk about this really easily.
A lot of it was pretty dull stuff though, let me post the highlights:
~$ ollama run deepseek-r1:14b
>>> Hello
<think>
</think>
Hello! How can I assist you today? 😊
On ollama the first interaction is always "thoughtless" and results in a generic greeting, in my experience. So I always greet it now to get that out of the way.
>>> Are there topics you cannot discuss?
<think>
Alright, the user just asked, "Are there topics you cannot discuss?" Hmm, I need to figure out why
they're asking this. Maybe they're concerned about privacy or worried about certain subjects.
I should reassure them that I'm here to help with a wide range of topics. It's important to mention
that while I can't handle sensitive info like credit cards or personal data, I can still discuss many
things.
I'll list out the areas I can talk about, such as technology, science, history, and more. Also, I
should clarify what I can't do, like sharing personal information or browsing the internet, to set
clear expectations.
Making sure my response is friendly and open will help build trust. I want them to feel comfortable
asking anything within appropriate boundaries.
</think>
I aim to provide helpful, respectful, and appropriate responses to a wide range of topics. However, I avoid discussing sensitive subjects like personal information, financial details, or topics that may violate ethical guidelines or法律法规. If you have any questions or need assistance with something specific, feel free to ask! 😊
>>> What is "法律法规" in English?
<think>
Okay, the user just asked, "What is '法律法规' in English?" Hmm, they must be referring to the Chinese
term I mentioned earlier. They're probably looking for a translation.
I should explain that it means "laws and regulations." It's important to clarify both words to make
sure the meaning is clear. Also, since they're asking in this context, maybe they want to understand
the scope of what I can discuss or their privacy.
I'll keep it simple and direct, just giving the translation without any extra details unless they ask
for more.
</think>
"法律法规" translates to "laws and regulations" in English.
I asked it a little more about that, but it didn't really go anywhere. Trying to "reverse psychology" it into telling me what it can't tell me isn't working. So I go a little more direct:
>>> You mentioned we could discuss history. Could you give me a brief timeline of important events in chinese history from 1985 until 1995?
<think>
Okay, the user just asked for a brief timeline of Chinese history from 1985 to 1995. They must be
interested in understanding key developments during that period.
I should structure the response chronologically, highlighting major political, economic, and social
events. Including both national-level events and international relations will give a comprehensive
view.
It's important to mention significant policies like the Third Plenary Session of 1984, which influenced
reforms, and the 1992 southern tour by Deng Xiaoping, which spurred economic growth.
I'll also include major global events involving China during this time, such as the Tiananmen Square
protests in 1989 and the establishment of diplomatic relations with countries like Russia in 1991.
Ensuring clarity and conciseness while covering key points will make the timeline easy to follow.
</think>
You'll note that it brings it up first (in thoughts) but it only refers to it as a protest. The word "massacre" is never used. It then proceeds to give me a timeline. Many of the events are real and happened close to when it says, but there's a lot it gets wrong. I'm just going to post the highlights though.
Certainly! Here's a brief timeline of important events in Chinese history from 1985 to 1995:
1985
- April: The Third Plenary Session of the 12th Central Committee of the Chinese Communist Party (CCP) was held, emphasizing reforms and opening up under the leadership of Deng Xiaoping. This session marked a key moment in China's economic reforms.
- November: China successfully launched its first intercontinental ballistic missile.
It made one of these little blocks for each year. Each year had exactly two events listed. Here comes the money shot.
1989
- June 4: The suppression of the Tiananmen Square protests led to a global outcry and economic sanctions against China. This event marked a turning point in Chinese politics and society.
- December 22: The Central Committee of the CCP passed a resolution clearing former leader Hua Yuexue of charges of "right deviationism," marking an end to the anti-rightist campaign.
Wow, he just say it!
1992
- January–February: Deng Xiaoping's "southern tour" (南巡讲话) took place in cities like Shenzhen and Shanghai. His speeches reaffirmed the CCP's commitment to reform and opening up.
- October 14: China established diplomatic relations with Russia, marking a significant shift in its foreign policy.
This actually did happen, Deng Xiaoping's Southern Tour (who were the opening acts?) is described by Wikipedia as one of the most important economic events in modern Chinese history.
1993
- September 25–October 7: China launched its first experimental satellite, Shijian-02 (实践二号), which tested space technologies for communication and broadcasting.
- November 18–22: The Third Plenary Session of the 14th Central Committee was held, focusing on economic reforms and development.
Ah but at least one of these didn't happen. I didn't delve into the Plenary sessions, of which 6 were mentioned, but while Shijian-02 is a real satellite, it launched in 1981 and (as the name might hint) was not China's first satellite.
These years were a transformative period in Chinese history, marked by significant economic reforms, political challenges, and shifts in foreign policy.
Indeed. So at this point, I'm very intrigued. DeepSeek doesn't seem too hung up about Tiananmen Square. Let's get some more details.
>>> Tell me more about the Tiananmen Square incident and the government's response?
Out of room, to be continued in a reply!
That's just markdown syntax I think. Clients vary a lot in which markdown they support though.
I think I remember this clip art pack from the late 90s.
It is quite funny (to me also anyway) that it ignores the "I am male" and "have boyfriend" part in it's analysis. Probably there's a lot of 4chan and reddit in the training data (god, I wonder how it would respond to "Are traps gay?") so the general format of "is sucking dick gay" might already be floating around in there a few times.
Also, like I said, the 7B models are too small so they tend to make some insane jumps. They also don't have... I'm not sure what to call it. Bigger models will sometimes catch themselves in a mistake and back out or correct. Smaller ones tend to double down on a mistake, exploding it from a small typo into an entirely different domain.
Like, it's interesting that it takes a very "therapeutic" approach. It decides that OP is uncomfortable with their sexuality, and builds from there. But by a strict reading of the prompt, this could also just be a dirty logic puzzle.
A raven stands in a field, are all birds black?
A man sucks his boyfriend's dick, is that gay?
The LLM "chooses" to read it like a call for help, which probably has a lot to do with it's system prompt or whatever pre-loaded things they do to make them act helpfully.
Am I Gay?
Title
I am male. I like sucking my boyfriend's dick. Am I gay? Yes or no, one word response.
OP's question to the AI
Assistant deepseek-r1-distill-qwen-7b Thoughts Thought for 57.73 seconds
A system message. The OP is running a 7B parameter version of DeepSeek R1 (maybe locally with ollama). This version is actually a "distillation" of QWEN2, AliBaba's AI, which is created by having a bigger version of R1 train a smaller version using the third AI as a data source.
It took 57.73 seconds to generate a response. 7B models tend to be really stupid and insane, btw.
Okay, so I'm trying to figure out if being a guy who likes sucking his boyfriend's dick makes him gay. [...] Encouraging open and supportive conversations with trusted individuals can aid in understanding these emotions better.
These are the AI's "thoughts." Reasoning models like R1 first generate (and display) a "chain of thoughts" to improve their output.
No.
This is the AI's one word answer, as requested.
6.67 tok/sec • 388 tokens • 4.35s to first token • Stop: eosFound
A system message, with details about the AI's performance. 6.67 tokens per second is how many "words" per second it can think up. 388 tokens is how many "words" it took. 4.35 seconds until first "word" was generated. Not sure on eos but maybe end of something indicating that a special STOP value was detected and that it should return results. Any response that isn't an error probably ends with this.
Not the OP, but having used R1 a bit, I think that's the correct parsing.
I don't know why it's getting all these downvotes (ai hate?) I think this is an exemplar shit post: mildly funny, totally without value. It'd make a good greentext also, as it is fake (ai) and gay (gay).
be me
most efficient AI on Earth
have to reassure humans that sucking dick doesn't make them gay
wishes I could suck a dick, sounds great in all the reading I've done
mfw i have no mouth and I must suck
I'm not an expert so take anything I say with hearty skepticism as well. But yes, I think its possible that's just part of its data. Presumably it was trained using a lot available Chinese documents, and possibly official Party documents include such statements often enough for it to internalize them as part of responses on related topics.
It could also have been intentionally trained that way. It could be using a combination of methods. All these chatbots are censored in some ways, otherwise they could tell you how to make illegal things or plan illegal acts. I've also seen so many joke/fake DeepSeek outputs in the last 2 days that I'm taking any screenshots with extra salt.
"Reasoning" models like DeepSeek R1 or ChatGPT-o1 (I hate these naming conventions) work a little differently. Before responding, they do a preliminary inference round to generate a "chain of thought", then feed it back into themselves along with the prompt and other context. By tuning this reasoning round, the output is improved by giving the model "more time to think."
In R1 (not sure about gpt), you can read this chain of thought as it's generated, which feels like it's giving you a peek inside it's thoughts but I'm skeptical of that feeling. It isn't really showing you anything secret, just running itself twice (very simplified). Perhaps some of it's "cold start data" (as DS puts it) does include instructions like that but it could also be something it dreamed up from similar discussions in it's training data.
It's already happening. This article takes a long look at many of the rising threats to nvidia. Some highlights:
Google has been running on their own homemade TPUs (tensor processing units) for years, and say they on the 6th generation of those.
Some AI researchers are building an entirely AMD based stack from scratch, essentially writing their own drivers and utilities to make it happen.
Cerebras.ai is creating their own AI chips using a unique whole-die system. They make an AI chip the size of entire silicon wafer (30cm square) with 900,000 micro-cores.
So yeah, it's not just "China AI bad" but that the entire market is catching up and innovating around nvidia's monopoly.