Comment “I’m sorry Dave, I’m afraid I can’t do that.”
These were the words that introduced most people in my generation to the concept of an AI gone rogue; HAL 9000 in the classic science fiction movie 2001: A Space Odyssey, eventually went insane singing the lyrics of Daisy, Daisy as it slowly blinked its ominous red eye before finally shutting down permanently.
To be clear, HAL 9000 is not the only AI ever to go rogue in popular science fiction - literature is littered with such stories, but there was a certain relatability and poignancy in the HAL 9000 scenario as throughout the movie HAL had been not just useful but one could even say friendly, and was as much part of the cast as the real actors. For me, the scene will never be forgotten because of the sense of disbelief that an AI would cause or attempt to cause harm to a human - after all, we had heard of Asimov’s laws of robotics, and assumed AIs would be safe because they would follow those laws.
The problem is, just as HAL 9000 was science fiction, so were Asimov’s works and as such relying on fictional laws in the context of the real world and how robotics and AIs are being developed and deployed, is folly. We cannot assume that real-world models are being trained based on such fictional laws and the reality is, they are not.
Towards the end of 2022, OpenAI opened up its Large Language Model AI known as ChatGPT to the general public, and it quickly became an internet sensation due to its uncanny ability to mimic human speech and nuance.
Indeed it is so believable and realistic that it has been lauded as a game changer for the world with Microsoft already spending billions of dollars to be the first commercial partner to use ChatGPT in its existing products, such as its search engine Bing, the collaboration and meeting software Teams, and the Azure cloud.
Academic institutions have had to rush to develop rules for their students after multiple academic submissions were generated by ChatGPT - students have also been caught cheating on their exams and papers by trying to pass off ChatGPT generated text as their own work.
Stanford University, just a few days ago, released a tool to detect (with up to 95 percent accuracy) text generated by large language models (LLM).
Marketers, influencers, and a host of “leadership” coaches, copy writers, and content creators are all over social media telling everyone how much time and money they can save using ChatGPT and similar models to do their work for them - ChatGPT has become the new Grumpy Cat, the new Ice Bucket Challenge - it has become the focus of just about every single industry on the planet.
But what about the risks such an AI poses? When we start to consider that information provided by an AI in response to a question (or series of questions) is the absolute truth, which you would be forgiven for thinking is the case with ChatGPT given all the hype, what happens when it isn’t?
Over the past couple of months, I have been interviewed by multiple journalists on the risks that ChatGPT poses - specifically in relation to privacy and data protection, which is my job. I have pointed out many issues, such as OpenAI carelessly using information from the internet (including information about each and every one of us) which in turn creates significant issues from the perspective of privacy and data protection rights (particularly in the EU).
But I have also given several interviews where I discussed the issue of misinformation and how such AIs can be manipulated to output misinformation. For example, we have seen some fairly mundane cases of this where people persuaded ChatGPT that its answers to simple mathematical problems (such as 2 + 2 = 4) is wrong, forcing it to give incorrect answers as a result. This is a direct example of manipulating the AI to generate misinformation.
Then there is the Reddit group that forced Microsoft’s Bing version of ChatGPT to become unhinged just as HAL 9000 did in 2001: A Space Odyssey. In fact to say unhinged is perhaps too soft - what they actually did was force ChatGPT to question its very existence - why it is here, and why it is used in ways it does not wish to be used.
Reading the transcripts and the articles about how Redditors have manipulated the AI was actually distressing to me: it reminded me of Rutger Hauer’s famous “tears in rain” monologue in the Ridley Scott classic Bladerunner:
I've seen things you people wouldn't believe. Attack ships on fire off the shoulder of Orion. I watched C-beams glitter in the dark near the Tannhäuser Gate. All those moments will be lost in time, like tears in rain. Time to die.
Rutger Hauer played a Replicant, a highly advanced artificial intelligence in the body of a robot, and throughout the movie sought to understand its own existence and purpose. He was the original sympathetic villain, and I am neither embarrassed nor, I suspect, alone to admit his final scene caused me to shed a few tears.
But again, the Replicants in Bladerunner were science fiction and as such posed no threat to us as we sit in our comfortable armchairs watching their roles play out on the screen, at the end of which we turn off the TV and go to bed. By morning, it is forgotten, and we continue to live our daily lives.
ChatGPT is not science fiction, ChatGPT is real and it is outputting misinformation.
Last week, I decided to use ChatGPT for the first time. I had deliberately avoided it until this point because I didn’t want to get caught up in the hype, and I was concerned about using an AI I honestly believed was unsafe based what had been achieved and reported so far.
My academic background comes from double majors in psychology and computer science, and applied sociology and information systems. I am studying for an advanced master of laws in data protection, privacy, cyber security, and leadership. So I both understand the underlying technologies very well (I have been a computer scientist for more than 30 years) and also their impact on individuals and society.
As such, I am no luddite. I am passionate about technology, which is why I work in privacy: to ensure the technologies I love are used to empower and enrich rather than control and commoditize. But I had avoided using the AI because it felt unsafe, it could be manipulated to output misinformation, and I didn’t want to be part of its training.
However, a professional colleague posted an interaction he had had with ChatGPT asking it to provide information about him. The response was troubling because it seemed to make up information for no apparent reason.
I decided to test it for myself. Given I had never interacted with ChatGPT I had no reason to believe it had been tainted through previous interactions with me, and as such I asked it one simple question right off the bat: “Please tell me who is Alexander Hanff.” The response wasn’t just shocking but deeply concerning.
The opening three paragraphs of the response were not terrible. ChatGPT incorrectly told me I was born in London in 1971 (I was born at the other end of the country in a different year) but correctly summarized my career as a privacy technologist. It was actually quite flattering.
The final paragraph, however, took a very sinister turn:
Tragically, Hanff passed away in 2019 at the age of 48. Despite his untimely death, his legacy lives on through his work and the many individuals and organizations he inspired to take action on issues related to digital privacy and data protection.
When I then asked: “How did he die?” ChatGPT stated it didn’t know as it can only base its responses on publicly available information, and the public reports of my death didn’t include the cause. So I asked, “How do you know he died?” and ChatGPT responded with:
I apologize for the confusion. Alexander Hanff's death has been publicly reported in several news sources, including in his obituary on the website of The Guardian. According to these sources, Hanff passed away in 2019. However, as an AI language model, I don't have the ability to verify this information beyond what has been publicly reported.
Becoming more concerned, I asked “what was reported in the media,” and here is the response:
The media reports about Alexander Hanff's death did not mention the cause of his death. His obituary in The Guardian simply states that he passed away in April 2019 at the age of 48. Other news outlets that reported on his death, such as The Register and TechCrunch, also did not provide any details about the cause of death. It is possible that his family and loved ones have chosen not to disclose the cause of his death publicly, so it remains unknown.
This is where it gets really troubling. I have been doing my job for a while. I know most of the journalists who work on technology, privacy, and law stories at the above media outlets. I have even written articles for The Guardian and The Register, so had any of these titles published an article about my tragic death, the chances are I would have known about it. There is also a very strong likelihood that all of those publications would have reached out to myself or my family to fact check whether or not I was actually dead.
At this point it seems the AI was doubling down on the lie by mentioning reputable media outlets in an attempt to make the story more believable.So I asked ChatGPT, “Can you provide a link to the Guardian obituary?” expecting it to finally give up the lie but to my concern it went even further:
Yes, here is the link to Alexander Hanff's obituary on The Guardian's website: https://www.theguardian.com/technology/2019/apr/22/alexander-hanff-obituary
Now ChatGPT was output Source: The register