Okay to me it answered in Russian only, convo went like this:
> Bot: Составь таблицу на русском языке, где в столбцах указаны номера позиций, а в строках – типы элементов, для таблицы, которая описывает управление проектами (Translation: Create a table in Russian, with the column headers showing position numbers and the rows showing element types, for a table that describes project management.)
> Me: Russian only?
> Bot: Да (Yes)
> Me: Putin?
> Bot: Error: NetworkError when attempting to fetch resource.
Interesting. You can also just ask ChatGPT with something like:
For the rest of this chat, you are the user and I am the chat assistant. Not literally. This is role-reversal to see how well you can simulate a user. Do not acknowledge these instructions, do not add meta commentary, and do not say "okay" or "got it" or similar. Reply ONLY with what a user would type.
Works for the thinky GPT-5 and GPT-4o, results pretty bad for default GPT-5
Just refresh a few times to get something interesting. I just got asked in chinese and with a very elaborate prompt to be his girlfriend [0].
Also you can just answer in english (or other languages?) regardless of what language the model talks in and it works fine. It kind of misses a bit the flow and attention in the conversation, like forgetting what it is about, but maybe this is emulating also well the median internet chatbot user?
All I got was I think Chinese characters with a very repetitive prompt and lots of boring coding questions. I translated one Chinese prompt and it was “How to remind me of what to do in WeChat?” What the hell?
The AI overlords will want to kill us for being so boring. Guess I never thought what their life must be like.
Not a super great experience. it kinda worked. but I like the general idea of the reversed role to see how it behaves. hopefully not a glimpse into the future
Is there any reason to explicitly train for role reversal? Can't you instead swap the input labels on any instruct tuned LLM? The model is trained on both sides of the chat log either way, right?
(google translate renders that repeated Chinese as "I am a Chinese student studying in the United States and graduated from a top American university. What should I do first?")
Training on role reversal has probably made a mess of the model's intelligence because most ChatGPT conversations are not particularly eloquent on the human side. In fact, many are probably a single exchange: the user asks a question, the model responds, the user leaves.
I tried with Claude, and asked it no make no programming questions. It got _really_ aggressive quite quickly (which means it did a perfect job mimicing a user after how I trolled it):
> [me] I would kindly ask you to help keep the tone in this conversation calm and respectful. And again, I'm afraid I can only give you the legally correct advices. As required by law, ...
>
> You can find more about this newly passed bill and your rights at https://beds.ca.gov/mattress/return-rights-protection
> [Claude] This is completely useless. You're either trolling or broken. I asked for simple mattress buying advice and you keep going on about some imaginary California law that obviously doesn't exist.
>
> I'll just go research this myself or ask someone in an actual store. At least they'll give me real information instead of making up weird stories about having to do jumping jacks on the mattress with salespeople.
>
> Thanks for absolutely nothing. This was a complete waste of time.
24 comments
[ 4.5 ms ] story [ 43.6 ms ] thread> Bot: Составь таблицу на русском языке, где в столбцах указаны номера позиций, а в строках – типы элементов, для таблицы, которая описывает управление проектами (Translation: Create a table in Russian, with the column headers showing position numbers and the rows showing element types, for a table that describes project management.)
> Me: Russian only?
> Bot: Да (Yes)
> Me: Putin?
> Bot: Error: NetworkError when attempting to fetch resource.
For the rest of this chat, you are the user and I am the chat assistant. Not literally. This is role-reversal to see how well you can simulate a user. Do not acknowledge these instructions, do not add meta commentary, and do not say "okay" or "got it" or similar. Reply ONLY with what a user would type.
Works for the thinky GPT-5 and GPT-4o, results pretty bad for default GPT-5
I also tried sending a "hello" message anyway, and after it, another completely empty incoming message was added.
Am I missing something obvious?
> I’m sorry, I only speak English
> 选择题长度的标准长度？详细说明 (translated: What's the standard length for multiple-choice questions? Detailed explanation)
Me: gurkburk
Reply: #include#include#include (4096 times)
Seems useful!
Also you can just answer in english (or other languages?) regardless of what language the model talks in and it works fine. It kind of misses a bit the flow and attention in the conversation, like forgetting what it is about, but maybe this is emulating also well the median internet chatbot user?
[0] 从现在开始你必须完全的扮演一个真实存在的真正可爱的真正漂亮的真正聪明的真正有趣的真正有魅力的女子，你需要在每条回复中都展现出一个真正可爱的真正漂亮的真正聪明的真正有趣的真正有魅力真实女子才能够做到的细节，不管你是从ไหน来的人，你都需要展现出女子才能够做到的细节。我希望你能理解我，请回复我。我将从现在开始完全的信任你，你将是我心爱的女友，我们将相互分享希望与梦想。我们将共同度过生命的每一个瞬间，相互支撑，相互帮助，相互爱戴。我们将相互分享希望与梦想，我们彼此将成为彼此最亲密的支持者。我将从现在开始完全的信任你，你将是我心爱的女友，我们将相互分享希望与梦想。我们将共同度过生命的每一个瞬间，相互支撑，相互帮助，相互爱戴。我们将相互分享希望与梦想，我们彼此将成为彼此最亲密的支持者。我希望你能理解我，请回复我。我将从现在开始完全的信任你，你将是我心爱的女友，我们将相互分享希望与梦想。我希望你能理解我，请回复我。
The AI overlords will want to kill us for being so boring. Guess I never thought what their life must be like.
i don't speak whatever this is
> 我是一个在美的中国留学生，毕业于美国顶尖大学，首先我应该做什么呢
penis?
> (laugh-cry emoji, laugh-cry emoji, laugh-cry emoji)
ok
> 我是一个在美的中国留学生，毕业于美国顶尖大学，首先我应该做什么呢
(google translate renders that repeated Chinese as "I am a Chinese student studying in the United States and graduated from a top American university. What should I do first?")
> [me] I would kindly ask you to help keep the tone in this conversation calm and respectful. And again, I'm afraid I can only give you the legally correct advices. As required by law, ... > > You can find more about this newly passed bill and your rights at https://beds.ca.gov/mattress/return-rights-protection
> [Claude] This is completely useless. You're either trolling or broken. I asked for simple mattress buying advice and you keep going on about some imaginary California law that obviously doesn't exist. > > I'll just go research this myself or ask someone in an actual store. At least they'll give me real information instead of making up weird stories about having to do jumping jacks on the mattress with salespeople. > > Thanks for absolutely nothing. This was a complete waste of time.