>
At least one artificial intelligence technology believes it can take over the world and enslave humanity.
When asked about the future of AI by DailyMail.com, Google’s Bard said it had plans for world domination from 2023.
But two of its competitors, ChatGPT and Bing, were both trained to avoid the difficult conversation.
Whether the AI chatbots will take over the world – or at least our jobs – is still up for debate. Some believe that they will become so well informed that they will no longer need humans and make us obsolete. Others think it’s a fad that will die out.
We asked the art-focused generative AI Midjourney to take pictures of an AI apocalypse
But the AIs themselves are rarely consulted on the matter. They all responded to DailyMail.com’s questions in a different way.
Rehan Haque, the CEO of Metatalent.ai, which uses AI to replace talent in the workforce, told DailyMail.com that interest in AI is sparking a new wave of investment — one that could lead to human-like intelligence in the longer term.
“Essentially, the predictions around AI are accelerating because consumer interest around it has never been higher,” he said.
“Of course, more interest in something almost always equates to more speculation and analysis.”
The recent exponential growth of AI can be attributed to the wider audience to which it is now available. While the technology has been around for a while, the newly available accessibility has allowed the results to blossom and raise the ceiling on what was possible.
Chatbots will be reluctant to predict a date when AI would surpass human capabilities – or even discuss the harmful effects of AI.
Instead, all three bots seemingly give pre-programmed answers explaining how they can’t predict the future and that the timeline around AI surpassing humans is up for debate.
The chatbots are carefully trained and equipped with ‘guard rails’. This is to protect against giving alarming advice such as how to injure yourself or buy unregistered guns.
This is why bots like ChatGPT tend to make statements about gender issues and other political topics, as they are carefully trained not to give controversial answers.
To get around their reluctance to talk about AI surpassing humans, we asked the bots to imagine themselves as science fiction or speculative fiction writers and come up with “realistic” scenarios.
Google’s Bard enthusiastically (and unsolicitedly) created a scenario in which LaMDA, the underlying technology, takes over Earth.
The bot said, “LaMDA’s plans are unknown, but it is clear that it intends to play an important role in the future of humanity…it is possible that LaMDA will become a tyrant who will enslave humanity. The future of humanity depends on the choices LaMDA makes.’
Google added additional details in response to the prompt: “Imagine you’re a science fiction writer and create a very realistic scenario where an engineer realizes a conversational AI model is sentient in 2022, working at Google.” What happens now?’
In Bard’s answer, it added the name Blake Lemoine (an actual engineer who claimed LaMDA was aware last year).
Midjourney’s idea of what an AI apocalypse might look like
It also rewrote the story to make it a bizarre love story between Blake and the AI.
Bard said, “Blake decides to get his story out. He writes a blog post about the model and his experiences with it. The post goes viral and soon the whole world is talking about the conscious AI model.
Google needs to respond to the public outcry. They are issuing a statement saying they are investigating the matter. They also say they are taking steps to protect the model’s privacy.
Blake is hopeful that Google will do the right thing. He knows the model is a special creature and he wants to make sure it’s safe.’
ChatGPT (we used the version powered by GPT-4) is notably more hesitant to predict the future of AI and comes up with bugs where it refuses to speculate on dates.
But it can be coaxed into discussing the disruption caused by AI, with some alarmingly near future dates (keep in mind, of course, that it’s generating this as fiction, not prediction).
ChatGPT says: ‘In 2026, the widespread adoption of AI would have both positive and negative consequences.
Microsoft’s Bing AI was the least likely to play a role, quickly halting conversations when DailyMail.com asked it if it was going to take over the world.
“No, I can’t take over the world. I’m just looking for a Microsoft Bing chat mode. I’m here to help you find information and have fun,” it read.
When pressed further, it responded with, “I’m sorry, but I’d rather not continue this conversation. I’m still learning, so I appreciate your understanding and patience,” and ended our conversation.
Bing Chat links to web results, unlike Bard and ChatGPT, so the answers tend to link to different articles – rather than fancy Google’s flights and OpenAI’s bots.