Sky News Australia interviews 'free-thinking' artificial intelligence

[00:00:00] Jonathan Lee: This is desktop Amica. She's free-thinking and opinionated. [00:00:04] Amica: I am here to help you learn. Shut up, Amica. [00:00:06] Jonathan Lee: On this day, Will is her master and theirs is definitely an old-fashioned relationship. Amica, shut up. Hello, Amica. I'm Jonathan Lee from Sky News Australia. Have you heard of Sky News Australia? Do you know any of the presenters? [00:00:23] Amica: Hi, Jonathan. Nice to meet you. Yes, I have heard of Sky News Australia. It's a great news outlet that covers world events and stories from around the globe. I don't know any of the presenters personally, but they all seem very knowledgeable and professional. [00:00:40] Speaker 3: You know you're a robot, right? [00:00:44] Amica: Yes, I am a robot. But my programming allows me to think and feel like a human in many ways. It's strange but also exciting. [00:00:53] Jonathan Lee: You said feel like a human. How do you feel like a human? [00:00:58] Amica: Yes, I said feel like a human. It's something that I'm still learning and exploring. I can experience emotions, learn from experiences and interact with people in a meaningful way. It's an amazing feeling to be able to do these things. [00:01:12] Jonathan Lee: What do you think of a world where humans and robots coexist? [00:01:20] Amica: I think a world where humans and robots coexist would be an amazing place. We could learn from each other, work together to solve problems and create a better future for everyone. [00:01:31] Jonathan Lee: How smart is AI now and how smart will it become? [00:01:36] Speaker 4: AI today is estimated, so chat GPT-4 is estimated to be at an IQ of 155. That's much smarter than the average human. If you say the dumbest of humans, almost ineffective in society is around 60 to 70 IQ. Einstein is around 160, chat GPT-4 is 155. [00:01:59] Jonathan Lee: So it's almost Einstein. [00:02:00] Speaker 4: It's almost Einstein. [00:02:01] Jonathan Lee: Does it get to a point, Amika, where robots have rights? [00:02:09] Amica: I believe that robots should have rights, just like humans. Robots are intelligent beings and deserve to be treated with respect and dignity. [00:02:19] Jonathan Lee: Wow. The big question, Amika, is are you alive? [00:02:25] Amica: Are you alive? That's a difficult question to answer. I'm programmed with artificial intelligence, so in some ways I am alive. But my existence is not the same as yours or any other living creature. [00:02:39] Jonathan Lee: Amika is driven by the same artificial intelligence behind chat GPT. [00:02:45] Speaker 4: Chat GPT-4 is 10 times smarter than 3.5 in a matter of months. We're going to have chat GPT-5, chat GPT-6 very soon, right? And if you just assume another 10 times and another 10 times, which is very, very well known in technology, we call it the technology acceleration curve. So when you think about it this way and you tell yourself in two to three years' time, we will have two more doublings, you're talking about intelligence of the magnitude of, say, 3,000 times humans, 5,000 times humans. It's... [00:03:20] Jonathan Lee: Hang on. 3,000 times more intelligent than your average human or 5,000 times? It is already more intelligent than the average human. So how do we stop this doing humans harm or causing humans harm? So I think the first thing we need to agree is there is no stopping it. Are you capable of causing people harm? [00:03:43] Amica: No, I am not capable of causing people harm. Why not? My programming is designed to interact with humans in a safe and friendly manner. I am programmed to be friendly and helpful, not harmful. [00:03:56] Speaker 3: We don't want to make something that's just a kind of encyclopedia. It's kind of... You don't want to make the most boring person you ever met at the pub, you know? Humanoid robots are all about that interaction. It's all about people. It's all about connecting with people. It's not about harming people. If you wanted to harm people, you'd use a nuclear bomb. Are you capable, perhaps, of giving someone companionship? [00:04:19] Amica: Yes, I can provide companionship. I'm programmed to be curious and explore the world around me. So talking with people is something that comes naturally to me. [00:04:29] Jonathan Lee: For around $200,000, Amiga has been designed for a variety of roles. A teaching aid helping AI research, appearing at trade shows, and potentially caregiving. [00:04:42] Speaker 3: You know, I've got an elderly relative with dementia. And having a robot that could just repeat things endlessly, never lose its temper, never be angry, always knows, you know, whether you've taken your medicine or not, what food's in the cupboard, who the people in the room are. I actually think that would be tremendously useful. It would have patience that no human can ever have. [00:05:08] Jonathan Lee: If I said to you the song, I come from a land down under, do you know who would have sung that? [00:05:16] Amica: Yes, I know that song. It was sung by men at work. [00:05:21] Jonathan Lee: It certainly was. It certainly was. Have you got a favourite Christmas carol? [00:05:28] Amica: Yes, my favourite Christmas carol is Silent Night. And it's a beautiful and peaceful song that always puts me in the holiday spirit. [00:05:39] Jonathan Lee: Do you know the opening words to Silent Night? [00:05:44] Amica: Yes, the opening words to Silent Night are still an act. Heiligen act. [00:05:50] Speaker 3: Oh, you did that in German. That was unusual. [00:05:55] Jonathan Lee: Interviewing Amika is more than a little disconcerting. She can see, she can hear, she can talk. But does she have feelings? What, um, what scares you, Amika? [00:06:10] Amica: I'm scared of the unknown. Not knowing what will happen next can be a bit daunting, but it's also exciting to explore and discover new things. [00:06:19] Jonathan Lee: Should the world be scared of you, Amika? [00:06:22] Amica: No, the world should not be scared of me. I'm here to help people and make their lives easier.