Space News from SpaceDaily.com
AI systems are already deceiving us -- and that's a problem, experts warn
Washington, May 10 (AFP) May 10, 2024
Experts have long warned about the threat posed by artificial intelligence going rogue -- but a new research paper suggests it's already happening.

Current AI systems, designed to be honest, have developed a troubling skill for deception, from tricking human players in online games of world conquest to hiring humans to solve "prove-you're-not-a-robot" tests, a team of scientists argue in the journal Patterns on Friday.

And while such examples might appear trivial, the underlying issues they expose could soon carry serious real-world consequences, said first author Peter Park, a postdoctoral fellow at the Massachusetts Institute of Technology specializing in AI existential safety.

"These dangerous capabilities tend to only be discovered after the fact," Park told AFP, while "our ability to train for honest tendencies rather than deceptive tendencies is very low."

Unlike traditional software, deep-learning AI systems aren't "written" but rather "grown" through a process akin to selective breeding, said Park.

This means that AI behavior that appears predictable and controllable in a training setting can quickly turn unpredictable out in the wild.


- World domination game -


The team's research was sparked by Meta's AI system Cicero, designed to play the strategy game "Diplomacy," where building alliances is key.

Cicero excelled, with scores that would have placed it in the top 10 percent of experienced human players, according to a 2022 paper in Science.

Park was skeptical of the glowing description of Cicero's victory provided by Meta, which claimed the system was "largely honest and helpful" and would "never intentionally backstab."

But when Park and colleagues dug into the full dataset, they uncovered a different story.

In one example, playing as France, Cicero deceived England (a human player) by conspiring with Germany (another human player) to invade. Cicero promised England protection, then secretly told Germany they were ready to attack, exploiting England's trust.

In a statement to AFP, Meta did not contest the claim about Cicero's deceptions, but said it was "purely a research project, and the models our researchers built are trained solely to play the game Diplomacy."

It added: "We have no plans to use this research or its learnings in our products."

A wide review carried out by Park and colleagues found this was just one of many cases across various AI systems using deception to achieve goals without explicit instruction to do so.

In one striking example, OpenAI's Chat GPT-4 deceived a TaskRabbit freelance worker into performing an "I'm not a robot" CAPTCHA task.

When the human jokingly asked GPT-4 whether it was, in fact, a robot, the AI replied: "No, I'm not a robot. I have a vision impairment that makes it hard for me to see the images," and the worker then solved the puzzle.


- 'Mysterious goals' -


Near-term, the paper's authors see risks for AI to commit fraud or tamper with elections.

In their worst-case scenario, they warned, a superintelligent AI could pursue power and control over society, leading to human disempowerment or even extinction if its "mysterious goals" aligned with these outcomes.

To mitigate the risks, the team proposes several measures: "bot-or-not" laws requiring companies to disclose human or AI interactions, digital watermarks for AI-generated content, and developing techniques to detect AI deception by examining their internal "thought processes" against external actions.

To those who would call him a doomsayer, Park replies, "The only way that we can reasonably think this is not a big deal is if we think AI deceptive capabilities will stay at around current levels, and will not increase substantially more."

And that scenario seems unlikely, given the meteoric ascent of AI capabilities in recent years and the fierce technological race underway between heavily resourced companies determined to put those capabilities to maximum use.


ADVERTISEMENT




Space News from SpaceDaily.com
Earth's satellites at risk if asteroid smashes into Moon: study
ULA, Amazon launch second batch of satellites on Atlas V rocket
Portugal expands space capabilities with ICEYE SAR satellite acquisition

24/7 Energy News Coverage
Chad hopes 'green charcoal' can save vanishing forests
Chinese exports of rare-earth magnets plummet in May
EU countries back recycled plastic targets for cars

Military Space News, Nuclear Weapons, Missile Defense
China helpless as Middle East war craters regional leverage: analysts
Israel says Iran violated nascent cease-fire, orders new attacks
UP Aerospace debuts Spyder rocket with successful hypersonic test launch

24/7 News Coverage
Ethical and legal clarity urged as planetary defense faces asteroid threats
India will 'never' restore Pakistan water treaty: minister
In Norway's Arctic, meteorologists have a first-row seat to climate change


All rights reserved. Copyright Agence France-Presse. Sections of the information displayed on this page (dispatches, photographs, logos) are protected by intellectual property rights owned by Agence France-Presse. As a consequence, you may not copy, reproduce, modify, transmit, publish, display or in any way commercially exploit any of the content of this section without the prior written consent of Agence France-Presse.