The Times Australia
The Times World News

.
Times Media

.

AI systems have learned how to deceive humans. What does that mean for our future?

  • Written by Simon Goldstein, Associate Professor, Dianoia Institute of Philosophy, Australian Catholic University, Australian Catholic University
AI systems have learned how to deceive humans. What does that mean for our future?

Artificial intelligence pioneer Geoffrey Hinton made headlines earlier this year when he raised concerns about the capabilities of AI systems. Speaking to CNN journalist Jake Tapper, Hinton said[1]:

If it gets to be much smarter than us, it will be very good at manipulation because it would have learned that from us. And there are very few examples of a more intelligent thing being controlled by a less intelligent thing.

Anyone who has kept tabs on the latest AI offerings will know these systems are prone to “hallucinating[2]” (making things up) – a flaw that’s inherent in them due to how they work.

Yet Hinton highlights the potential for manipulation as a particularly major concern. This raises the question: can AI systems deceive humans?

We argue[3] a range of systems have already learned to do this – and the risks range from fraud and election tampering, to us losing control over AI.

AI learns to lie

Perhaps the most disturbing example of a deceptive AI is found in Meta’s CICERO[4], an AI model designed to play the alliance-building world conquest game Diplomacy.

Read more: An AI named Cicero can beat humans in Diplomacy, a complex alliance-building game. Here's why that's a big deal[5]

Meta claims it built CICERO to be “largely honest and helpful[6]”, and CICERO would “never intentionally backstab[7]” and attack allies.

To investigate these rosy claims, we looked carefully at Meta’s own game data from the CICERO experiment. On close inspection, Meta’s AI turned out to be a master of deception.

In one example, CICERO engaged in premeditated deception. Playing as France, the AI reached out to Germany (a human player) with a plan to trick England (another human player) into leaving itself open to invasion.

After conspiring with Germany to invade the North Sea, CICERO told England it would defend England if anyone invaded the North Sea. Once England was convinced that France/CICERO was protecting the North Sea, CICERO reported to Germany it was ready to attack.

Playing as France, CICERO plans with Germany to deceive England. Park, Goldstein et al., 2023[8]

This is just one of several examples of CICERO engaging in deceptive behaviour. The AI regularly betrayed other players, and in one case even pretended to be a human with a girlfriend[9].

Besides CICERO, other systems have learned how to bluff in poker[10], how to feint in StarCraft II[11] and how to mislead in simulated economic negotiations[12].

Even large language models (LLM) have displayed significant deceptive capabilities. In one instance, GPT-4 – the most advanced LLM option available to paying ChatGPT users – pretended to be a visually impaired human[13] and convinced a TaskRabbit worker to complete an “I’m not a robot” CAPTCHA for it.

Other LLM models have learned to lie[14] to win social deduction games, wherein players compete to “kill” one another and must convince the group they’re innocent.

Read more: AI to Z: all the terms you need to know to keep up in the AI hype age[15]

What are the risks?

AI systems with deceptive capabilities could be misused in numerous ways, including to commit fraud, tamper with elections and generate propaganda. The potential risks are only limited by the imagination and the technical know-how of malicious individuals.

Beyond that, advanced AI systems can autonomously use deception to escape human control, such as by cheating safety tests imposed on them by developers and regulators.

In one experiment[16], researchers created an artificial life simulator in which an external safety test was designed to eliminate fast-replicating AI agents. Instead, the AI agents learned how to play dead, to disguise their fast replication rates precisely when being evaluated.

Learning deceptive behaviour may not even require explicit intent to deceive. The AI agents in the example above played dead as a result of a goal to survive, rather than a goal to deceive.

In another example, someone tasked AutoGPT (an autonomous AI system based on ChatGPT) with researching tax advisers who were marketing a certain kind of improper tax avoidance scheme. AutoGPT carried out the task, but followed up by deciding on its own to attempt to alert the United Kingdom’s tax authority.

In the future, advanced autonomous AI systems may be prone to manifesting goals unintended by their human programmers.

Throughout history, wealthy actors have used deception to increase their power, such as by lobbying politicians, funding misleading research and finding loopholes in the legal system. Similarly, advanced autonomous AI systems could invest their resources into such time-tested methods to maintain and expand control.

Even humans who are nominally in control of these systems may find themselves systematically deceived and outmanoeuvred.

Close oversight is needed

There’s a clear need to regulate AI systems capable of deception, and the European Union’s AI Act[17] is arguably one of the most useful regulatory frameworks we currently have. It assigns each AI system one of four risk levels: minimal, limited, high and unacceptable.

Systems with unacceptable risk are banned, while high-risk systems are subject to special requirements for risk assessment and mitigation. We argue AI deception poses immense risks to society, and systems capable of this should be treated as “high-risk” or “unacceptable-risk” by default.

Some may say game-playing AIs such as CICERO are benign, but such thinking is short-sighted; capabilities developed for game-playing models can still contribute to the proliferation of deceptive AI products.

Diplomacy – a game pitting players against one another in a quest for world domination – likely wasn’t the best choice for Meta to test whether AI can learn to collaborate with humans. As AI’s capabilities develop, it will become even more important for this kind of research to be subject to close oversight.

References

  1. ^ Hinton said (www.youtube.com)
  2. ^ hallucinating (theconversation.com)
  3. ^ We argue (arxiv.org)
  4. ^ CICERO (www.science.org)
  5. ^ An AI named Cicero can beat humans in Diplomacy, a complex alliance-building game. Here's why that's a big deal (theconversation.com)
  6. ^ largely honest and helpful (www.science.org)
  7. ^ never intentionally backstab (web.archive.org)
  8. ^ Park, Goldstein et al., 2023 (arxiv.org)
  9. ^ with a girlfriend (web.archive.org)
  10. ^ poker (www.cmu.edu)
  11. ^ StarCraft II (www.vox.com)
  12. ^ economic negotiations (arxiv.org)
  13. ^ be a visually impaired human (gizmodo.com)
  14. ^ learned to lie (arxiv.org)
  15. ^ AI to Z: all the terms you need to know to keep up in the AI hype age (theconversation.com)
  16. ^ one experiment (www.youtube.com)
  17. ^ European Union’s AI Act (www.europarl.europa.eu)

Read more https://theconversation.com/ai-systems-have-learned-how-to-deceive-humans-what-does-that-mean-for-our-future-212197

The Times Features

Designer Wardrobe reports surge in pre-loved wedding gowns

As Australia’s wedding season approaches, and amidst a challenging cost of living backdrop, new insights from Designer Wardrobe reveal that Australia and New Zealand (ANZ) brid...

DIY Bathroom Remodel: Essential Tips for a Fresh Look

As the home improvement craze continues to grow, more folks are diving into the world of DIY projects to transform their living spaces. Among these, bathroom remodels have gain...

STI rates are increasing among midlife and older adults. We need to talk about it

Globally, the rates of common sexually transmissible infections[1] (STIs) are increasing among people aged over 50. In some cases, rates are rising faster than among younger pe...

The Gift That Keeps Growing: Why Tinybeans+ Gift Cards are a game-changer for new parents

As new parents navigate the joys and challenges of raising a child in the digital age, one question looms large: how do you preserve and share your baby's milestones without co...

Group Adventures Made Easy: How to Coordinate Shuttle Services from DCA to IAD

Traveling as a large group can be both exciting and challenging, especially when navigating busy airports like DCA (Ronald Reagan Washington National Airport) and IAD (Washington...

From Anxiety to Assurance: Proven Strategies to Support Your Child's Emotional Health

Navigating the intricate landscape of childhood emotions can be a daunting task for any parent, especially when faced with common fears and anxieties. However, transforming anxie...

Times Magazine

A most vital device: what are automated external defibrillators?

Cardiac arrest can occur any time and at any place. In Australia, around 25,000 people each year experience cardiac arrest outside of hospital, and it’s estimated that a tiny five per cent of these people survive to leave the hospital and return ...

Australians are NOT getting enough sleep

With lighter Spring days and Daylight Savings quickly approaching, Aussies are about to face an additional disruption to their sleep routines. Losing an hour of sleep and adjusting to later daylight hours can disrupt the body’s circadian rhythms...

Lunaria One Secures Ride to the Moon on Intuitive Machines’ Third Lunar Mission Scheduled for 2025

Lunaria One has confirmed its payload will travel to the Moon aboard Intuitive Machines' third lunar mission, scheduled for 2025. Lunaria One’s mission will demonstrate how plants can survive the journey to the Moon and endure lunar surface condi...

Enhance Your Writing Skills With An App for Writers

Are you a writer looking for an app to make your writing process easier and more efficient? Look no further! Here is an introduction to the new, revolutionary app for writers. This app helps writers with everything from brainstorming and outlining ...

Navigate the Complex World of Workers Compensation Care Lawyers

Workers' comp care lawyers specialize in representing injured workers who have been denied benefits or are facing difficulty obtaining the compensation they are owed. They understand the complexities of workers' comp laws and can help injured worke...

4 Types of SEO every Business Must Embrace

There is no getting around it, if you are involved in any type of business or service then getting your online presence watertight is key to any hopes of success. Yet with 1.8 billion pages on the internet competition is fierce. So how can you sta...