Al Mayadeen English

  • Ar
  • Es
  • x
Al Mayadeen English

Slogan

  • News
    • Politics
    • Economy
    • Sports
    • Arts&Culture
    • Health
    • Miscellaneous
    • Technology
    • Environment
  • Articles
    • Opinion
    • Analysis
    • Blog
    • Features
  • Videos
    • NewsFeed
    • Video Features
    • Explainers
    • TV
    • Digital Series
  • Infographs
  • In Pictures
  • • LIVE
News
  • Politics
  • Economy
  • Sports
  • Arts&Culture
  • Health
  • Miscellaneous
  • Technology
  • Environment
Articles
  • Opinion
  • Analysis
  • Blog
  • Features
Videos
  • NewsFeed
  • Video Features
  • Explainers
  • TV
  • Digital Series
Infographs
In Pictures
  • Africa
  • Asia
  • Asia-Pacific
  • Europe
  • Latin America
  • MENA
  • Palestine
  • US & Canada
BREAKING
Russian Ministry of Defense: 37 Ukrainian drones destroyed in 4 hours over regions of Russia and the Black Sea.
Sheikh Qassem: Our supporters make up more than half of Lebanon's population, and all of these people are united under the banner of protecting Lebanon, its Resistance, its people, and its integrity.
Sheikh Qassem: There will be no phased handing in of our arms. [The Israelis] must first enact the agreement before we start talking about a defensive strategy.
Sheikh Qassem: Be brave in the face of foreign pressures, and we will be by your side in this stance.
Sheikh Qassem: Stripping us of our arms is like stripping us of our very soul, and this will prompt us to show them our might.
Sheikh Qassem: We will not abandon our arms, for they gave us dignity; we will not abandon our arms, for they protect us against our enemy.
Sheikh Qassem: The US efforts we are seeing are aimed at sabotaging Lebanon and constitute a call for sedition.
Sheikh Qassem: If you truly want to establish sovereignty and work for Lebanon’s interests, then stop the aggression.
Sheikh Qassem: The United States, which is meddling in Lebanon, is not trustworthy but rather poses a danger to it.
Sheikh Qassem: The United States is preventing the weapons that protect the homeland.

AI increasingly learning to deceive humans: MIT study

  • By Al Mayadeen English
  • Source: News websites
  • 11 May 2024 09:40
4 Min Read

Scientists are warning of the dangers of artificial intelligence (AI) as its constant developments are increasing its capacity for deception, such as bluffing in games or pretending to be human to deceive people.

  • x
  • Microsoft CEO Satya Nadella speaks during a conference in Kuala Lumpur, Malaysia, Thursday, May 2, 2024. (AP)
    Microsoft CEO Satya Nadella speaks during a conference in Kuala Lumpur, Malaysia, on Thursday, May 2, 2024. (AP)

Scientists are warning of the dangers of artificial intelligence (AI) as its constant developments are increasing its capacity for deception, according to an analysis by Massachusetts Institute of Technology (MIT) researchers, which located multiple attempts such as double-crossing opponents in games, bluffing, and pretending to be human.

Dr. Peter Park, an AI existential safety researcher at MIT and author of the research, stated, “As the deceptive capabilities of AI systems become more advanced, the dangers they pose to society will become increasingly serious,” as he investigated the matter following Meta's development of the Cicero program which performed in the top 10% of human players at the world conquest strategy game Diplomacy.

According to Meta, Cicero was trained to be “largely honest and helpful” and to “never intentionally backstab” its human allies, but Park said, “It was very rosy language, which was suspicious because backstabbing is one of the most important concepts in the game."

During the research, Park and his associates looked through publicly available data and identified multiple instances of Cicero lying premeditatedly, colluding to draw other players into its plots and, in one instance, justifying its absence after being rebooted by telling another player, “I am on the phone with my girlfriend.”

“We found that Meta’s AI had learned to be a master of deception,” Park stressed. 

A spokesperson for Meta said, “Our Cicero work was purely a research project and the models our researchers built are trained solely to play the game Diplomacy … Meta regularly shares the results of our research to validate them and enable others to build responsibly off of our advances. We have no plans to use this research or its learnings in our products.”

Read more: Suicide-inspiring misusage of AI may grow into a pattern: UN

Related News

Musk’s xAI sues Apple, OpenAI over antitrust collusion in AI market

Russia urges global action to curb AI use by terrorist groups

'It's not me, it's AI'

One study revealed that AI in a digital simulator “played dead” in an attempt to trick a test meant to eliminate AI systems that had evolved to replicate, before resuming activity once testing was complete.

“That’s very concerning,” said Park, noting, “Just because an AI system is deemed safe in the test environment doesn’t mean it’s safe in the wild. It could just be pretending to be safe in the test.”

Published in the journal Patterns, the research urges governments to establish AI safety laws addressing AI deception's capacities as risks include fraud, tampering with elections, and “sandbagging” where multiple users are provided different responses. The research warned that humans could lose control of it. 

Professor Anthony Cohn, a professor of automated reasoning at the University of Leeds and the Alan Turing Institute, called the study “timely and welcome."

“Desirable attributes for an AI system (the “three Hs”) are often noted as being honesty, helpfulness, and harmlessness, but as has already been remarked upon in the literature, these qualities can be in opposition to each other: being honest might cause harm to someone’s feelings, or being helpful in responding to a question about how to build a bomb could cause harm,” he said.

“So, deceit can sometimes be a desirable property of an AI system. The authors call for more research into how to control the truthfulness which, though challenging, would be a step towards limiting their potentially harmful effects.”

Back in May of last year, a statement released by the Center for AI Safety warned that AI technology should be classified as a societal risk and put in the same class as pandemics and nuclear wars.

Read more: Shut down AI or 'everyone on Earth will die', researcher warns

  • Artificial Intelligence
  • technology
  • MIT
  • fraud

Most Read

Tom Artiom Alexandrovich, executive director of the defense division of the Israeli National Cyber Directorate, undated (Social media)

Israeli-born US prosecutor drops Israeli officer child sex crime

  • Politics
  • 19 Aug 2025
Almost instantly after the Helsinki Accords were signed, organisations sprouted to document purported violations, whose findings were fed to overseas embassies for international amplification. (Al Mayadeen English; Illustrated by Zeinab el-Hajj)

How ‘Human Rights’ became a Western weapon

  • Opinion
  • 23 Aug 2025
Israeli soldiers stand on the top of armoured vehicles parked on an area near the Israeli-Gaza border, as seen from southern Israel, Wednesday, Aug. 20, 2025 (AP)

Palestinian fighters target Israeli soldiers, vehicles in Gaza

  • Politics
  • 21 Aug 2025
Launch of a ballistic missile from Yemen toward the occupied Palestinian territories. (YAF military media)

Yemeni Forces announce firing hypersonic missile at Al-Lydd Airport

  • Politics
  • 22 Aug 2025

Coverage

All
The Ummah's Martyrs

Read Next

All
Israeli Prime Minister Benjamin Netanyahu speaks during a press conference at the Prime minister's office in al-Quds, Occupied Palestine, Sunday, Aug. 10, 2025 (AP)
Politics

Netanyahu deliberately derailing truce with Gaza occupation: Hamas

Irish President Michael Higgins arrives to deliver his speech during a 42nd World Food Day celebration at FAO headquarters in Rome, on Oct. 16, 2023. (AP Photo/Alessandra Tarantino)
Politics

Irish president renews call for UN military intervention in Gaza

US Ambassador to Turkey and Special Envoy to Syria Tom Barrack speaks during an interview with The Associated Press at the US Embassy in Aukar, northern suburb of Beirut, Lebanon, Monday, July 21, 2025 (AP)
Politics

US envoy, Netanyahu discuss restraining attacks on Lebanon, withdrawal

Smoke billows following Israeli airstrikes in multiple areas in Sanaa, Yemen, Sunday, Aug. 24, 2025 (AP)
Politics

Ansar Allah vow sustained Gaza support despite Israeli strikes

Al Mayadeen English

Al Mayadeen is an Arab Independent Media Satellite Channel.

All Rights Reserved

  • x
  • Privacy Policy
  • About Us
  • Contact Us
  • Authors
Android
iOS