Skip to main content

You can fool some of the people all of the time: AIs and deception

 


Two papers that each consider trust and AIs are of interest, the first is 'Suspicious Minds: The Problem of Trust and Conversational Agents' by Jonas Ivarsson, University of Gothenburg. The second by Rogers and Webber, "Lying About Lying: Examining Trust Repair Strategies After Robot Deception in a High Stakes HRI Scenario". 

Artificial intelligence is getting so good at talking that it's hard to tell the difference between humans and machines.

It can now be difficult to know who you're talking to. 'Consequently, the ‘Turing test’ has moved from the laboratory into the wild', as Ivarsson states, If you think you're talking to a human, but it's actually a machine, you might share personal information that you wouldn't want to share with a machine.

This is also a problem because it can erode trust in human-to-human interactions. If people can't tell the difference between humans and machines, they might start to distrust each other.

'Therefore, this study concludes that the proliferation of conversational systems, fueled by artificial intelligence, may have unintended consequences, including impacts on human–human interactions.'

The issues that Ivarsson explored are only exacerbated by the topic of the second paper, as Webber states in this:

"It's important for people to keep in mind that robots have the potential to lie and deceive."

This study looked at how humans react when a robot lies to them. The study found that people are more likely to change their behavior if they are told that the robot is lying, and that an apology without acknowledging intentional deception is the best way to repair trust.

Designers and policy makers need to consider GPTs current abilities to deceive and what the implications are, even before we get to robots. 

In two to three years time, as manufacturers imbue more and more of your everyday technology with AI 'assistants', your phones, cars, TVs, etcetera, and you realise that they are lying to you, what will the human response be? Will their apologies be sufficient?





Comments

Popular posts from this blog

The Whispers in the Machine: Why Prompt Injection Remains a Persistent Threat to LLMs

 Large Language Models (LLMs) are rapidly transforming how we interact with technology, offering incredible potential for tasks ranging from content creation to complex analysis. However, as these powerful tools become more integrated into our lives, so too do the novel security challenges they present. Among these, prompt injection attacks stand out as a particularly persistent and evolving threat. These attacks, as one recent paper (Safety at Scale: A Comprehensive Survey of Large Model Safety https://arxiv.org/abs/2502.05206) highlights, involve subtly manipulating LLMs to deviate from their intended purpose, and the methods are becoming increasingly sophisticated. At its core, a prompt injection attack involves embedding a malicious instruction within an otherwise normal request, tricking the LLM into producing unintended – and potentially harmful – outputs. Think of it as slipping a secret, contradictory instruction into a seemingly harmless conversation. What makes prompt inj...

Can We Build a Safe Superintelligence? Safe Superintelligence Inc. Raises Intriguing Questions

  Safe Superintelligence Inc . (SSI) has burst onto the scene with a bold mission: to create the world's first safe superintelligence (SSI). Their (Ilya Sutskever, Daniel Gross, Daniel Levy) ambition is undeniable, but before we all sign up to join their "cracked team," let's delve deeper into the potential issues with their approach. One of the most critical questions is defining "safe" superintelligence. What values would guide this powerful AI? How can we ensure it aligns with the complex and often contradictory desires of humanity?  After all, "safe" for one person might mean environmental protection, while another might prioritise economic growth, even if it harms the environment.  Finding universal values that a superintelligence could adhere to is a significant hurdle that SSI hasn't fully addressed. Another potential pitfall lies in SSI's desire to rapidly advance capabilities while prioritising safety.  Imagine a Formula One car wi...

AI Agents and the Latest Silicon Valley Hype

In what appears to be yet another grandiose proclamation from the tech industry, Google has released a whitepaper extolling the virtues of what they're calling "Generative AI agents". (https://www.aibase.com/news/14498) Whilst the basic premise—distinguishing between AI models and agents—holds water, one must approach these sweeping claims with considerable caution. Let's begin with the fundamentals. Yes, AI models like Large Language Models do indeed process information and generate outputs. That much isn't controversial. However, the leap from these essentially sophisticated pattern-matching systems to autonomous "agents" requires rather more scrutiny than the tech evangelists would have us believe. The whitepaper's architectural approaches—with their rather grandiose names like "ReAct" and "Tree of Thought"—sound remarkably like repackaged versions of long-standing computer science concepts, dressed up in fashionable AI clot...