Artificial Intelligence, or AI, seems to have finally arrived. With the introduction of ChatGPT last November, millions of people suddenly discovered that AI was far, far more than just a research activity. The range and sophistication of ChatGPT’s answers to questions across a wide range of disciplines is, frankly, pretty stunning.
AI is already in lots of places where you might not even realize it. Google Translate has been using AI for years, and it’s remarkably good, although nowhere near as good as a human translator. The technology that Pandora uses to customize your music is a type of AI, as is the technology behind Tesla’s self-driving cars. Within my own field, the program AlphaFold2 was a true breakthrough in scientists’ ability to predict the structure of proteins.
Along with these apparently beneficial developments, though, comes a great deal of concern. As AI gets better and better, can we continue to trust it to make decisions for us? It’s one thing if an AI recommends a song that we don’t like, which we can just ignore, but if AI is driving our cars, then mistakes might be much more costly.
And there are far riskier tasks that AI might be doing soon: what if the military starts using AI on the battlefield? One might be tempted to say no, of course they won’t do that, but what if another country starts using AI this way? Can we simply ignore that?
To be honest, I haven’t been worried, at least not yet. I have a little secret to confess: I did my Ph.D. thesis in AI, in the area called machine learning. I haven’t been doing AI research for the past 25 years, but I think I still understand at least a little of the basics behind the technology.
Thanks mostly to the attention that ChatGPT is getting, though, there’s suddenly a huge concern that AI represents a danger to society, although no one is exactly sure why. President Biden had a meeting just this week with the CEOs of Google, Microsoft, and OpenAI (the creators of ChatGPT) to talk about these concerns, where he told the execs that “What you’re doing has enormous potential and enormous danger.”
Of course, politicians have no idea what AI technology is–although I had to laugh at this quote from the White House press secretary: “The president has been extensively briefed on ChatGPT and knows how it works.” Well no, he doesn’t, but I’m skeptical that the CEOs of Google and Microsoft know how it works either. However, you don’t need to understand the technology to understand the dangers.
Just recently, one of AI’s early pioneers, Geoffrey Hinton, has been speaking out to warn the public that AI has reached a point where “there’s a danger of something really bad happening.” Not surprisingly, other experts, such as German scientist Jürgen Schmidhuber, disagree.
The chair of the FTC, Lina Khan, says we can regulate AI effectively, and perhaps we can. But I’m not so sure that regulation will eliminate the dangers that Geoffrey Hinton is worried about.
Much of the concern in the press seems to be about the use of AI to spread misinformation. For example, AI can help create “deep fakes” that can be used to convince people that, say, an election was stolen even when it wasn’t. That’s a legitimate concern, but it’s happening even without AI.
A better question, which a family member just asked me, is should we be worried about AI making decisions on the battlefield? I thought I should take this question directly to the source, so I asked ChatGPT itself. The answer I got was remarkably clear and direct; I’ll quote it here in full:
“Yes, people should be concerned about AI making decisions on the battlefield. There are several reasons for this.
Firstly, AI lacks human empathy, judgment, and intuition. In a complex and dynamic environment such as the battlefield, human decision-making is often guided by experience, intuition, and an understanding of the broader context. AI lacks the ability to consider these intangible factors and may make decisions solely based on pre-programmed algorithms or data inputs, which could lead to unintended consequences or even catastrophic errors.
Secondly, the use of AI in military decision-making raises significant ethical concerns. For instance, an AI system may be programmed to prioritize the protection of friendly forces at the expense of civilian lives, leading to potentially devastating consequences for non-combatants caught in the crossfire. Additionally, AI systems may be susceptible to hacking or manipulation, which could result in unintended consequences or a loss of control over the decision-making process.
Finally, there is the risk that reliance on AI systems may lead to the erosion of human decision-making capabilities, potentially diminishing the overall quality of military decision-making and increasing the likelihood of errors or unintended consequences.”
So there you have it: ChatGPT itself gives us several reasons why it’s a terrible idea to let AI make decisions that might cost human lives. We should listen to what it’s telling us, because as it gets more intelligent (and it will), it might decide not to be so honest in the future. And I have to say that it’s reasoning here is both well-written and compelling.
One thing that worries me as well is that the very term “artificial intelligence” is much too broad. We should be concerned about giving any technology the power to control our lives, whatever someone calls it. But when an AI itself says “don’t trust me,” then I think we might want to listen.