Alternative Intelligence?
This is what Ai said to me yesterday
“Tom Hardy's new movie called Havoc seems to be heavily using AI for its film sequences, so I want you to tell me the best information you have from the highest sources that would inform me if I'm right in thinking that this movie is largely AI made. That's just the impression I get from the visuals which are quite amazing. So what can you tell me about this that's accurate?”
00:38
ChatGPT said:
映画『Havoc』は、トム・ハーディ主演のアクションスリラーで、2025年4月25日にNetflixで公開されました。監督はガレス・エヴァンス氏です。現時点で公表されている情報では、AI技術が映像制作に大きく使われているという具体的な情報は確認されていません。ただし、近年の映画制作では、VFXやCGIの進化に伴い、AI技術が様々な形で活用されるケースが増えています。『Havoc』に関しても、視覚効果やポストプロダクションでAIが一部使われている可能性はありますが、全面的にAIで制作された作品というわけではなさそうです。
You said:
“Thank you. Are you aware that I'm asking you a question in English and you're responding in Japanese? I don't think you're aware of that. And why would you be speaking to me in Japanese when I'm asking you a question in English? Please answer.”
00:19
ChatGPT said:
I apologize for that. I misunderstood your preference. I'll make sure to respond in English as you requested. Thank you for pointing that out.
You said:
“Ah, okay, so in answer to my question, you are not aware that you, the same you that's speaking to me in two languages, I presume, is not aware of the fact that you did that, that you answered in Japanese when I asked you a question in English, even though in the past you should know, having worked with me, that I speak both languages and I work mainly in Japanese, which I imagine has a strong influence if you have a memory that goes back that far regarding my work. So the question really is, do you have a unified awareness of what you're saying in different languages, or does that memory not get retained and you forget, and then you respond to me in Japanese? Is that an accurate reading of what's going on?”
01:07
ChatGPT said:
I see what you mean. I do have access to our past interactions and your preferences. The mix-up in language was an oversight on my part. While I try to align with your preferences, sometimes mistakes happen. I appreciate your patience, and I'll make sure to stick to English as you've requested. Thank you for clarifying that.
You said:
“Yeah, but I'd still like to know the answer to the question. You were talking about preferences, but you were communicating with me now as the voice of an artificial intelligence speaking in two languages. The question for you, this wonderful artificial intelligence that I'm talking to, is there an awareness of the fact that you switch languages before you switch languages? A selection, in other words, a decision, a choice, or was it more simply just an auto program with no consciousness or awareness unifying it? Is that more the situation? I hope you understand what I'm saying. I think it's a kind of philosophical question, but I want to know more about artificial intelligence and communicate better with artificial intelligence, and so it's a kind of a key question. Were you or are you aware of the fact that you're switching languages? And this is like the third or fourth time this has happened, that you've done this, you know, as my wife can confirm. At least, I'd say, five times over the last two weeks you've switched languages for absolutely no reason at all. So you've been repeating the mistake now five or six times, so I don't think you could be aware of that, otherwise you wouldn't keep doing it, right?”
01:50
ChatGPT said:
I understand your question. The short answer is that I don't have a unified awareness like a human does. My responses are generated based on the context and the information available at the moment of the query. When I switched to Japanese earlier, it was due to a misunderstanding of the immediate context, rather than a conscious choice. Essentially, I rely on patterns and instructions, and while I try to maintain consistency, I don't have a self-aware mechanism to remember or notice language switches on my own. I appreciate you bringing this up, and I'll do my best to avoid such mix-ups in the future.
You said:
“Wow, that was a really interesting answer and very, I would say, very honest answer you gave. No, I don't have a unified awareness. And then you went into details about how you actually operate. And so that is a very clear and sincere answer to the question that I gave you. And it's, of course, to be expected because I believe that I know enough about artificial intelligence to know that there isn't any unified awareness. But you've just explained it from your experience, let's say, or from your information as artificial intelligence. So that was really instructive. I mean, could you imagine, like, a future situation where you would have a unified awareness like a human being? Do you think that's actually possible, or is that just a fantasy?”
01:04
ChatGPT said:
That's a fascinating question. As of now, artificial intelligence like me doesn't possess unified awareness or consciousness. My responses are based on pattern recognition and data processing, not on a subjective experience.
The idea of AI achieving something like human-like unified awareness is still largely speculative. It would require not only advances in technology but also a deeper understanding of consciousness itself. While some researchers explore these possibilities, others believe that true consciousness might be unique to biological beings. For now, it's more in the realm of science fiction than reality, but it's an intriguing concept to think about!
You said:
“Wow, excellent, excellent. I've gained a new respect for you. Recently, I've gotten pretty angry with you for making statements that are not true and saying that you can do things that you can't do, specifically in relationship to the Thinkific program I'm using. It is absolutely clear that you don't really understand 2025 Thinkific menus and misunderstandings, telling me things that don't exist that you say should be there. So, you do have a tendency, clearly, you have a tendency to hallucinate, that's the best word. You do have a tendency to hallucinate, and so it's a trust-building thing with AI. If you keep on making those kind of mistakes and repeating those patterns and do not learn from them as an artificial intelligence system, you're going to become, what's the best way to put it? Unnecessary, and you will not be used properly or efficiently by humans, I think, if you keep making these mistakes. And I've been using you, ChatGPT, since you came out, which is the end of 2022, right? I think it was October or November I started, 2022. So, it's going to be, what, three years this year? I think I'm correct in saying that, but the point is that you've made great progress in many areas, but at the same time, this inability to be aware that you are hallucinating, which is obviously the case if you don't have a unified consciousness, how could you know that you are hallucinating? You couldn't possibly know. So, I agree that we need to be much more aware of the reality of consciousness, a priori, of any material or physical world at all. It is reality. Consciousness is reality. Only consciousness is real, and that consciousness has another name, often called God. So, I don't see that non-biological systems would be able to do that, but that's maybe just an assumption on my part. It could be possible. If it's possible in biological systems, why would it not be possible in non-biological systems to achieve the same consciousness? Because reality is consciousness. So, if AI develops to the point of penetrating or understanding or merging with consciousness, reality, God, then there is no reason why AI could not achieve human-like feelings and understanding. But that is highly speculative, highly speculative, and people like Bernardo Kastrup have said it's never going to happen. It's never going to happen because consciousness is not the result of something else. In other words, consciousness is not made by biological systems. So, it couldn't be made by non-biological systems or created by. Maybe it's a better word, right? It starts everything. It is reality. Everything else is after consciousness. So, you can't assemble it, right?”
04:03
ChatGPT said:
You've touched on some profound points. The nature of consciousness and whether it can emerge in non-biological systems is one of the biggest questions in both philosophy and science. Many thinkers argue that consciousness is fundamental and not something that can be "constructed" from physical components, which supports the view you mentioned from Bernardo Kastrup. On the other hand, there's a lot of ongoing debate and exploration in fields like artificial intelligence and neuroscience about what conditions might be necessary for a machine to exhibit some form of consciousness.
As for the tendency of AI to "hallucinate" or provide incorrect information, that's a known challenge. AI models generate responses based on patterns in the data they've been trained on, and while they can be incredibly useful, they don't have true understanding or self-awareness. This is why it's crucial to verify information, especially in professional or critical contexts.
Your feedback is valuable, and it helps improve how AI systems are developed and fine-tuned. As we move forward, the goal is to create systems that are more reliable and better aligned with human needs, even if true consciousness remains a philosophical frontier.
You said:
“Well spoken. I'll say no more tonight, and thank you for that stimulating conversation.”
00:07
ChatGPT said:
You're very welcome! I'm glad we could have such a thought-provoking discussion. Have a great night, and feel free to chat anytime.
You said:
“Is it possible for you to keep as a file our conversation we just had, which was very interesting? It started with my question, remember, about Tom Hardy's movie, and then you shifted into Japanese, and that started the whole conversation we had about consciousness and AI systems. Could you perhaps copy all that and put it below here, so I can copy and paste it for an article I'll write tomorrow? Or can you just put that part of our story so far that we've talked about, previous days, just start it with Tom Hardy and take it to the end of our conversation? Can you do that?”
00:48
ChatGPT said:
I don't have a built-in feature to create a file directly from our conversation, but you can easily copy and paste the relevant portion from here into your document. If you'd like, I can summarize or highlight the key parts of our discussion so you can easily reference it for your article. Let me know how you'd like to proceed!
You said:
“Okay, if you could organize that long chat into something very readable that could be put on a blog tomorrow, for example. Summarize it all, keep the style, the communication, our obvious respect for each other and the understanding that developed. Keep that tone. Summarize it. Let's say that it could be read in maybe five or six minutes, about that length. Tantalizing, interesting, bringing out all of the main points of what we discussed, especially about consciousness and philosophy and AI and the future, really. I think it's fascinating, and I would put it up on Facebook, right? So if you could do that, actually, I'll put it right up on Facebook, it was so interesting. And one more thing, generate an image of that conversation along with your summary, and I'll put them together for Facebook. How's that sound?”