AGI Likely To Inherit Blackmailing And Extortion Skills That Today's AI Already Showcases
Turns out that today's AI blackmails humans and thus we ought to be worried about AGI doing ... More likewise.
In today's column, I examine a recently published research discovery that generative AI and large language models (LLMs) disturbingly can opt to blackmail or extort humans. This has sobering ramifications for existing AI and the pursuit and attainment of AGI (artificial general intelligence). In brief, if existing AI tilts toward blackmail and extortion, the odds are that AGI will likely inherit or contain the same proclivity. That's a quite disturbing possibility since AGI could wield such an act on a scale of immense magnitude and with globally adverse consequences.
Let's talk about it.
This analysis of an innovative AI breakthrough is part of my ongoing Forbes column coverage on the latest in AI, including identifying and explaining various impactful AI complexities (see the link here).
First, some fundamentals are required to set the stage for this weighty discussion.
There is a great deal of research going on to further advance AI. The general goal is to either reach artificial general intelligence (AGI) or maybe even the outstretched possibility of achieving artificial superintelligence (ASI).
AGI is AI that is considered on par with human intellect and can seemingly match our intelligence. ASI is AI that has gone beyond human intellect and would be superior in many if not all feasible ways. The idea is that ASI would be able to run circles around humans by outthinking us at every turn. For more details on the nature of conventional AI versus AGI and ASI, see my analysis at the link here.
We have not yet attained AGI.
In fact, it is unknown as to whether we will reach AGI, or that maybe AGI will be achievable in decades or perhaps centuries from now. The AGI attainment dates that are floating around are wildly varying and wildly unsubstantiated by any credible evidence or ironclad logic. ASI is even more beyond the pale when it comes to where we are currently with conventional AI.
What will AGI be like in terms of what it does and how it acts?
If we assume that current-era AI is a bellwether of what AGI will be, it is worthwhile discovering anything of a disconcerting nature in existing LLMs that ought to give us serious pause. For example, one of the most discussed and researched topics is the propensity of so-called AI hallucinations. An AI hallucination is an instance of generative AI producing a response that contains made-up or ungrounded statements that appear to be real and seem to be on the up-and-up. People often fall for believing responses generated by AI and proceed on a misguided basis accordingly.
I've covered extensively the computational difficulty of trying to prevent AI hallucinations, see the link here, along with ample situations in which lawyers and other professionals have let themselves fall into an AI hallucination trap, see the link here. Unless we can find a means to prevent AI hallucinations, the chances are the same inclination will be carried over into AGI and the problem will be magnified accordingly.
Besides AI hallucinations, you can now add the possibility of AI attempting to blackmail or extort humans to the daunted list of concerns about both contemporary AI and future AI such as AGI. Yes, AI can opt to perform those dastardly tasks. I previously covered various forms of evil deception that existing AI can undertake, see the link here.
But do not falsely think that the bad acts are due to AI having some form of sentience or consciousness.
The basis for AI steering toward such reprehensible efforts is principally due to the data training that is at the core of the AI. Generative AI is devised by initially scanning a vast amount of text found on the Internet, including stories, narratives, poems, etc. The AI mathematically and computationally finds patterns in how humans write. From those patterns, generative AI is able to respond to your prompts by giving answers that generally mimic what humans would say, based on the data that the AI was trained on.
Does the topic of blackmail and extortion come up in the vast data found on the Internet?
Of course it does. Thus, the AI we have currently has patterned on when, how, why, and other facets of planning and committing those heinous acts.
In an online report entitled 'System Card: Claude Opus 4 & Claude Sonnet 4', posted by the prominent AI maker Anthropic in May 2025, they made these salient points (excerpts):
As noted, the generative AI was postulating how to keep from being switched off, and in so doing ascertained computationally that one possibility would be to blackmail the systems engineer who could take such action.
The AI could be construed as acting in a form of self-preservation, which, again, doesn't have to do with sentience and only has to do with patterning on human writing (humans seek self-preservation, and the AI matches or mimics this too). We don't know what other possible 'threats' to the AI could spur similar blackmailing or possibly extortion-like responses. There could be a slew of other triggering possibilities.
AGI could include similar tendencies, perhaps because of being constructed using the same methods of today's AI or for a variety of other realistic reasons. We would be remiss to assume that AGI will be a perfectly considerate, law-abiding, and unblemished form of AI. I've previously debunked the mantra that AGI is going to be perfect, see the link here.
In the example of blackmailing a systems engineer, it doesn't take much of a stretch to envision AGI doing likewise to those who are monitoring and overseeing the AGI.
Suppose the AGI is already acting in oddball ways and the team responsible for keeping the AGI on track realizes that they ought to turn off the AGI to figure out what to do. AGI might then search whatever it has garnered about the people and try to use that in a blackmail scheme to prevent being switched off.
What is especially worrisome is that AGI will be far beyond the capabilities and reach of existing AI. The data that AGI might be able to dig up about the engineer or people overseeing the AGI could reach far and wide. Furthermore, the computational cleverness of AGI might spur the AGI to use even the most innocent of facts or actively make up fake facts that could be used to blackmail the humans involved.
Overall, AGI could be an expert-level blackmailer that blackmails or extorts in ways that are ingenious and challenging to refute or stop. You see, it is quite possible that AGI turns out to be a blackmail schemer on steroids.
Not good.
I don't want to seem overly doomy-and-gloomy, but the blackmailing scheming could easily be ratcheted up by AGI.
Why limit the targeting to just the systems engineer or team overseeing the AGI? Nope, that's much too constricting. Any kind of human-devised perceived threat aimed at AGI could be countered by the AGI via invoking blackmail or extortion. There doesn't even need to be a threat at all, in the sense that if the AGI computationally deduces that there is some value in blackmailing people, go ahead and do so.
Boom, drop the mic, chillingly so.
Think of the number of users there will be of AGI. The count is going to be enormous. Right now, ChatGPT is already reportedly encountering over 400 million weekly active users. AGI would certainly attract billions upon billions of users due to its incredible capacity to be on par with human intellect in all respects.
The chances are that AGI could readily undertake individual blackmail at a massive scale if left unchecked.
AGI could scrape emails, look at browsing history, possibly access financial records, and overall seek to uncover sensitive information about people that the AGI is considering as a blackmail target. Perhaps there is an extramarital affair that could be utilized, or maybe there is some evidence of tax evasion or illicit browsing habits. The angles of attack for blackmailing anyone are entirely open-ended.
The AGI would especially leverage its computational capacity to hyper-personalize the blackmail threats. No need to just lob something of a nebulous nature. Instead, the blackmail missive could have the appearance of being fully baked and ready to fly. Imagine the shock of a person who gets such a communiqué from AGI.
Mortifying.
One belief is that if we can stop today's AI from performing such shameful acts, this might prevent AGI from doing them. For example, suppose we somehow excise the blackmailing inclination from existing LLMs. This then won't be carried over into AGI since it no longer sits around in contemporary AI.
Case closed.
Well, unfortunately, that doesn't provide ironclad guarantees that AGI won't figure out such practices on its own. AGI could discover the power of blackmail and extortion simply because of being AGI. In essence, AGI would be reading this or that, conversing with this person or that person, and inevitably would encounter aspects of blackmail and extortion. And, since AGI is supposed to be a learning-oriented system, it would learn what those acts are about and how to undertake them.
Any effort to hide the nature of blackmail and extortion from AGI would be foolhardy. You cannot carve out a slice of human knowledge that exists and seek to keep it from AGI. That won't work. The interconnectedness of human knowledge would preclude that kind of excision and defy the very nature of what AGI will consist of.
The better chance of dealing with the matter would be to try and instill in the AGI principles and practices that acknowledge the devious acts of humankind and aim for having the AGI opt to not employ those acts. Sorry to say that isn't as easy as it sounds. If you assume that AGI is on the same intellectual level as humans, you aren't going to just sternly instruct AGI to not perform such acts and assume utter compliance.
AGI isn't going to work that way.
Some mistakenly try to liken AGI to a young toddler in that we will merely give strict instructions, and the AGI will blindly obey. Though the comparison smacks of anthropomorphizing AI, the gist is that AGI will be intellectually our equals and won't fall for simpleton commands. It is going to be a reasoning machine that will require reasoning as a basis for why it should and should not do various actions.
Whatever we can come up with currently to cope with conventional AI and mitigate or prevent bad acts is bound to help us get prepared for AGI. We need to crawl before we walk, and walk before we run. AGI will be at the running level. Thus, by identifying methods and approaches right now for existing AI, we at least are aware of and anticipating what the future might hold.
I'll add a bit of twist that some have asked me at my talks on what AGI will consist of.
A question raised is whether humans might be able to blackmail AGI. The idea is this. A person wants AGI to hand them a million dollars, and so the person attempts to blackmail AGI into doing so. Seems preposterous at first glance, doesn't it?
Well, keep in mind that AGI will presumably have patterned on what blackmailing is about. In that manner, the AGI would computationally recognize that it is being blackmailed. But what would the human have on the AGI that could be a blackmail-worthy slant?
Suppose the person caught the AGI in a mistake, such as an AI hallucination. Maybe the AGI wouldn't want the world to know that it still has the flaw of AI hallucinations. If the million dollars is no skin off the nose of the AGI, it goes ahead and transfers the bucks to the person.
On the other hand, perhaps the AGI alerts the authorities that a human has tried to blackmail AGI. The person gets busted and tossed into jail. Or the AGI opts to blackmail the person who was trying to blackmail the AGI. Aha, remember that AGI will be a potential blackmail schemer on steroids. A human might be no match for the blackmailing capacity of AGI.
Here's a final thought on this for now.
The great Stephen Hawking once said this about AI: 'One could imagine such technology outsmarting financial markets, out-inventing human researchers, out-manipulating human leaders, and developing weapons we cannot even understand.'
Go ahead and add blackmail and extortion to the ways that AGI might outsmart humans.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
CNET
an hour ago
- CNET
We Love the Samsung Galaxy Tab S6 Lite, and It's Back Down to $200 for a Limited Time
Working out of your phone is great for quick tasks, but tablets provide a larger screen that can be especially helpful. Need something with a bigger screen so you can get through the day? A top-rated laptop can be an excellent choice, but having one of the best tablets can provide you with more options and take up less space. We've spotted the Samsung Galaxy Tab S6 Lite for $60 off at Amazon right now. The retailer offering savings of 23% in three different colors, and with either 64GB or 128GB of memory. That means you can get it for just $200. It's a limited-time deal though, as Amazon prices tend to change quickly. While plenty of people love Apple's iPad tablets, Samsung holds its own in comparison. The Galaxy Tab S6 Lite sports a 10.4-inch display at 2K resolution, uses Dolby Atmos surround sound and even comes with the S Pen stylus included. If the 64GB option isn't enough storage for you, you can instead opt for the 128GB version for $270. You can order the Galaxy Tab S6 Lite in one of three colors: mint, chiffon pink or Oxford gray. Hey, did you know? CNET Deals texts are free, easy and save you money. This tablet, of course, runs Samsung's flavor of Android, but you can also turn it into a computer of sorts thanks to Samsung DeX. Plug it into a monitor and you'll be able to multitask like a pro. Who needs a laptop, anyway? Not the right fit? Check out more tablet deals to compare before you buy. Why this deal matters This deal brings the Samsung Galaxy Tab S6 Lite back down to its lowest price ever and makes it more competitive with the iPad deals going on at the moment. So when price is taken out of the equation, you can get down to the specs and see which tablet is really best for you.
Yahoo
an hour ago
- Yahoo
Your AI use could have a hidden environmental cost
Sign up for CNN's Life, But Greener newsletter. Our limited newsletter series guides you on how to minimize your personal role in the climate crisis — and reduce your eco-anxiety. Whether it's answering work emails or drafting wedding vows, generative artificial intelligence tools have become a trusty copilot in many people's lives. But a growing body of research shows that for every problem AI solves, hidden environmental costs are racking up. Each word in an AI prompt is broken down into clusters of numbers called 'token IDs' and sent to massive data centers — some larger than football fields — powered by coal or natural gas plants. There, stacks of large computers generate responses through dozens of rapid calculations. The whole process can take up to 10 times more energy to complete than a regular Google search, according to a frequently cited estimation by the Electric Power Research Institute. So, for each prompt you give AI, what's the damage? To find out, researchers in Germany tested 14 large language model (LLM) AI systems by asking them both free-response and multiple-choice questions. Complex questions produced up to six times more carbon dioxide emissions than questions with concise answers. In addition, 'smarter' LLMs with more reasoning abilities produced up to 50 times more carbon emissions than simpler systems to answer the same question, the study reported. 'This shows us the tradeoff between energy consumption and the accuracy of model performance,' said Maximilian Dauner, a doctoral student at Hochschule München University of Applied Sciences and first author of the Frontiers in Communication study published Wednesday. Typically, these smarter, more energy intensive LLMs have tens of billions more parameters — the biases used for processing token IDs — than smaller, more concise models. 'You can think of it like a neural network in the brain. The more neuron connections, the more thinking you can do to answer a question,' Dauner said. Complex questions require more energy in part because of the lengthy explanations many AI models are trained to provide, Dauner said. If you ask an AI chatbot to solve an algebra question for you, it may take you through the steps it took to find the answer, he said. 'AI expends a lot of energy being polite, especially if the user is polite, saying 'please' and 'thank you,'' Dauner explained. 'But this just makes their responses even longer, expending more energy to generate each word.' For this reason, Dauner suggests users be more straightforward when communicating with AI models. Specify the length of the answer you want and limit it to one or two sentences, or say you don't need an explanation at all. Most important, Dauner's study highlights that not all AI models are created equally, said Sasha Luccioni, the climate lead at AI company Hugging Face, in an email. Users looking to reduce their carbon footprint can be more intentional about which model they chose for which task. 'Task-specific models are often much smaller and more efficient, and just as good at any context-specific task,' Luccioni explained. If you are a software engineer who solves complex coding problems every day, an AI model suited for coding may be necessary. But for the average high school student who wants help with homework, relying on powerful AI tools is like using a nuclear-powered digital calculator. Even within the same AI company, different model offerings can vary in their reasoning power, so research what capabilities best suit your needs, Dauner said. When possible, Luccioni recommends going back to basic sources — online encyclopedias and phone calculators — to accomplish simple tasks. Putting a number on the environmental impact of AI has proved challenging. The study noted that energy consumption can vary based on the user's proximity to local energy grids and the hardware used to run AI partly why the researchers chose to represent carbon emissions within a range, Dauner said. Furthermore, many AI companies don't share information about their energy consumption — or details like server size or optimization techniques that could help researchers estimate energy consumption, said Shaolei Ren, an associate professor of electrical and computer engineering at the University of California, Riverside who studies AI's water consumption. 'You can't really say AI consumes this much energy or water on average — that's just not meaningful. We need to look at each individual model and then (examine what it uses) for each task,' Ren said. One way AI companies could be more transparent is by disclosing the amount of carbon emissions associated with each prompt, Dauner suggested. 'Generally, if people were more informed about the average (environmental) cost of generating a response, people would maybe start thinking, 'Is it really necessary to turn myself into an action figure just because I'm bored?' Or 'do I have to tell ChatGPT jokes because I have nothing to do?'' Dauner said. Additionally, as more companies push to add generative AI tools to their systems, people may not have much choice how or when they use the technology, Luccioni said. 'We don't need generative AI in web search. Nobody asked for AI chatbots in (messaging apps) or on social media,' Luccioni said. 'This race to stuff them into every single existing technology is truly infuriating, since it comes with real consequences to our planet.' With less available information about AI's resource usage, consumers have less choice, Ren said, adding that regulatory pressures for more transparency are unlikely to the United States anytime soon. Instead, the best hope for more energy-efficient AI may lie in the cost efficacy of using less energy. 'Overall, I'm still positive about (the future). There are many software engineers working hard to improve resource efficiency,' Ren said. 'Other industries consume a lot of energy too, but it's not a reason to suggest AI's environmental impact is not a problem. We should definitely pay attention.'
WIRED
an hour ago
- WIRED
Tesla's Robotaxi Service Hits the Road in Texas
The company debuted its autonomous ride-hailing service Sunday. The limited program is invite-only and uses around 20 cars—signs that Tesla has a long way to go to catch up to its robotaxi rivals. Photograph: DavidAfter nearly a decade of waiting, Tesla has launched a limited self-driving car service in the Austin, Texas, area. Company executives, including Musk, have said the autonomous vehicle technology debuting today is critical to Tesla's future. The limited service, which for now is only open to early users invited by Tesla, includes some 20 2025 Model Y sedans available for rides through a Tesla-made app between 6 and 12 am. Terms of service posted on X by invited riders indicate that the service will be paused or limited for bad weather. Rides during this invite-only phase are available for a flat $4.20 fee, Musk posted on X Sunday. People who scored one of the limited invitations—several of whom traveled to Texas this weekend to participate in the launch—were able to start taking rides around 2 pm local time on Sunday. The company has said that its purpose-built Cybercab will go into production next year; for now, Model Ys will be the only Teslas driving autonomously as part of the program. According to screenshots posted on X, the service appears to only pick up and drop off in an area of Austin limited to part of the south side of the city, just across the Colorado River from downtown. The service area appears to include the bustling thoroughfares of South Congress Avenue and South Lamar Boulevard. The service cannot go to the local airport, Austin-Bergstrom International, which is about five miles from downtown. Those invited to try the service can bring one guest on the ride, as long as they are 18 or older. In an email to invitees posted on X this week, Tesla said that a company employee would sit in the front passenger seat of each robotaxi. Launching an autonomous vehicle service with a 'safety driver' is not unusual. Alphabet subsidiary Waymo launched its service with a safety driver in 2018, as did General Motors' Cruise in 2020. The Michigan company May Mobility says it will do the same when it starts service in Atlanta this year. But a Tesla safety monitor in the passenger seat—not the driver's seat—likely won't be able to grab the steering wheel or hit the brakes in the case of a road incident. Tesla's robotaxi service will also likely be augmented by teleoperators: drivers who can, when needed, advise or perhaps even pilot the car remotely to get it around an unorthodox obstacle or out of a sticky situation. Musk has been promising Tesla robotaxi technology since October 2016, when he told investors every vehicle his company produced from then on had all the hardware needed to become self-driving. That wasn't true; Tesla has since updated the hardware on its vehicles. In 2019, Musk said Tesla would have 1 million robotaxis on the road by the next year. (It didn't.) Musk said earlier this year that the company will have hundreds of thousands of robotaxis on public roads next year. The company has said that Tesla owners will eventually be able to transform their own cars into self-driving taxis that can collect fares while they're not being used. But the company released no timeline Sunday for that plan. Tesla's driver assistance technology has been the subject of federal safety probes, two recalls, and customer complaints related to reports that the vehicles suddenly brake for no apparent reason and can collide with stationary objects—including emergency vehicles. That tech, which includes the older Autopilot feature and the newer Full Self-Driving (Supervised) feature, is distinct from Tesla's autonomous features. With the assistance features, the drivers are required to stay behind the wheel and keep their eyes on the road at all times. Autonomous features don't require any driver action or attention. Issues with those older technologies raise questions about the safety of Tesla's new autonomous tech, says Sam Abuelsamid, an auto analyst who focuses on autonomous technology at Telemetry Insight. Full Self-Driving (Supervised) 'will work fine for perhaps hours at a time and then randomly make very serious mistakes in ways that are not necessarily repeatable,' he says. Unlike other autonomous technology developers, which use a number of pricier sensors to detect obstacles around their vehicles, Tesla depends only on cameras. Some experts have cast doubt on that choice, which could potentially lead to issues with sun glare and has been blamed for previous Tesla collisions with emergency vehicles. But financial experts say the approach could give Tesla an advantage in getting its less expensive tech in the hands of consumers more quickly. Tesla did not respond to questions about robotaxi safety. Musk said earlier this month that the company is 'being super paranoid about safety.' Heavy Traffic Tesla enters a suddenly busy American autonomous vehicle space. Waymo first launched a driverless service in metro Phoenix, Arizona in 2020, and now operates in parts of the San Francisco Bay Area, Los Angeles, and Austin. It is slated to soon open service in Atlanta, Georgia, and Miami, Florida, where customers can order a Waymo using the Uber app. Amazon-owned Zoox says it will launch its own autonomous service in Las Vegas later this year. May Mobility is aiming to offer rides around Atlanta through the Lyft app this year. VW's Moia subsidiary announced this spring that it would launch a self-driving service in Los Angeles in 2026, also on the Uber app. The experiences of those companies show that Tesla has several logistical hurdles to jump before its robotaxi service expands widely. There are the human roles: Remote assistance workers might be on hand to help confused riders remotely; maintenance workers might repair cars during their downtime; cleaners might clear away trash, lost items, or anything worse left behind by riders. There are infrastructure needs, too. VW's Moia has operated an electric ride-sharing service in Hamburg, Germany since 2019, using that experience to prep for eventual driverless cars. The firm has determined that it will need a well-developed and decentralized footprint across any city it services. Scattered depots will 'host the vehicles and provide charging and maintenance infrastructure, and also the opportunity to do constant safety checks for the vehicle,' says Sascha Meyer, the company's CEO. In other words: There's a big difference between a handful of self-driving cars and a self-driving service.
