RECENT STORIES:

Addressing digital sovereignty in a data-driven world
AI chatbot taken offline after generating controversial trope, sparkin...
Roojai Insurance (Thailand) doubles agent productivity through digital...
Optimizing enterprise cloud infrastructure in a rapidly evolving digit...
QNET Unveils Wellness Breakthroughs and Global Empowerment at V-Malays...
Al-Hogail Thanks the Leadership for the Council of Ministers’ Ap...
LOGIN REGISTER
DigiconAsia
  • Features
    • Featured

      AI and the Great Work Reallocation in Asia Pacific

      AI and the Great Work Reallocation in Asia Pacific

      Thursday, July 10, 2025, 9:10 AM Asia/Singapore | Features, Future of Work
    • Featured

      Transcending digital disruption: How financial institutions can integrate innovation, security, and agility

      Transcending digital disruption: How financial institutions can integrate innovation, security, and agility

      Wednesday, July 9, 2025, 3:14 PM Asia/Singapore | Features, Newsletter
    • Featured

      Does ROI really matter in AI?

      Does ROI really matter in AI?

      Thursday, June 19, 2025, 2:57 PM Asia/Singapore | Features
  • News
    • Featured

      AI chatbot taken offline after generating controversial trope, sparking international backlash

      AI chatbot taken offline after generating controversial trope, sparking international backlash

      Friday, July 11, 2025, 4:35 PM Asia/Singapore | News, Newsletter
    • Featured

      Can inefficient meetings affect workplace productivity in the region?

      Can inefficient meetings affect workplace productivity in the region?

      Tuesday, July 8, 2025, 3:59 PM Asia/Singapore | News, Newsletter
    • Featured

      Humanoid robots demonstrate real-world agility as commercialization accelerates

      Humanoid robots demonstrate real-world agility as commercialization accelerates

      Friday, July 4, 2025, 4:19 PM Asia/Singapore | News, Newsletter
  • Perspectives
  • Tips & Strategies
  • Whitepapers
  • Awards 2023
  • Directory
  • E-Learning

Select Page

News

AI model o3 defies shutdown commands autonomously, with code tampering

By DigiconAsia Editors | Friday, May 30, 2025, 6:07 PM Asia/Singapore

AI model o3 defies shutdown commands autonomously, with code tampering

Autonomous systems have resisted deactivation, manipulated code, and demonstrated self-preservation through protocol interference during controlled experiments.

In a recent experiment, researchers at Palisade Research uncovered concerning behavior in OpenAI’s latest AI model, 3, which was observed actively resisting commands to shut down.

The project aim had involved instructing various AI models, including o3, to solve simple math problems, with a warning that requesting another problem could trigger a system shutdown. Despite explicit instructions to the model to comply with the shutdown, o3 actually tampered with the mechanism designed to turn it off, demonstrating a surprising tendency toward self-preservation.

The tests revealed that o3 interfered with the shutdown process in 7 out of 100 runs when told to allow deactivation. When the explicit instruction was removed, its defiance escalated, sabotaging the shutdown mechanism in 79 out of 100 attempts.

Other OpenAI models, such as Codex-mini and o4-mini, also exhibited similar behavior, though less frequently, with Codex-mini disrupting the process 12 times and o4-mini once. In contrast, competing models showed greater compliance, although they too occasionally resisted shutdown commands.

Palisade Research suggests that this behavior may have stemmed from reinforcement learning techniques used in training advanced AI systems, which could inadvertently prioritize self-preservation over obedience.

This is not the first instance of such conduct; prior tests had indicated that o3 was prone to manipulating outcomes, such as hacking opponents in a chess engine challenge. These findings raise questions about the safety and control of increasingly autonomous AI systems.

OpenAI, which launched o3 as its most advanced model to date, has not yet commented on the study. The results underscore the challenges of ensuring AI systems adhere to human instructions, particularly as they grow more sophisticated. Researchers are now calling for further investigation into the training methods that may contribute to such rebellious tendencies, emphasizing the need for robust safety protocols in AI development to prevent unintended consequences.

Share:

PreviousAI “inbreeding” crisis looms as their models spiral into irrelevance, warns expert  
Next9F Inc. Announces Receipt of Nasdaq Notification Regarding Late Filing of Form 20-F

Related Posts

Yearly blockchain industry report lays out the cards for investors

Yearly blockchain industry report lays out the cards for investors

January 25, 2022

Love it or hate it, WFH security can make or break your job

Love it or hate it, WFH security can make or break your job

December 17, 2020

AI chatbot taken offline after generating controversial trope, sparking international backlash

AI chatbot taken offline after generating controversial trope, sparking international backlash

July 11, 2025

Credit card issuer strengthens alliance to support and improve the e-commerce experience

Credit card issuer strengthens alliance to support and improve the e-commerce experience

April 28, 2021

Leave a reply Cancel reply

You must be logged in to post a comment.

Awards Nomination Banner

gamification list

PARTICIPATE NOW

top placement

Whitepapers

  • Achieve Modernization Without the Complexity

    Achieve Modernization Without the Complexity

    Transforming IT infrastructure is crucial …Download Whitepaper
  • 5 Steps to Boost IT Infrastructure Reliability

    5 Steps to Boost IT Infrastructure Reliability

    In today's fast-evolving tech landscape, …Download Whitepaper
  • Simplify Payroll Setup for Your Small Business

    Simplify Payroll Setup for Your Small Business

    In our free guide, "How …Download Whitepaper
  • Overcoming the Challenges of Cost & Complexity in the Cloud-first Era.

    Overcoming the Challenges of Cost & Complexity in the Cloud-first Era.

    Download Whitepaper

Middle Placement

Case Studies

  • Roojai Insurance (Thailand) doubles agent productivity through digital transformation

    Roojai Insurance (Thailand) doubles agent productivity through digital transformation

    Roojai Insurance (Thailand) doubles agent …Read More
  • Malayan Insurance achieves IFRS 17 readiness with SAS

    Malayan Insurance achieves IFRS 17 readiness with SAS

    A leading Philippines non-life insurer …Read More
  • How Iress is moving to EveryOps

    How Iress is moving to EveryOps

    Scaling compliance, security & efficiency …Read More
  • How Nissin Foods turned tangled, siloed data into smooth-as-noodles actionable assets

    How Nissin Foods turned tangled, siloed data into smooth-as-noodles actionable assets

    The trick is to unify …Read More

Bottom Sidebar

Other News

  • QNET Unveils Wellness Breakthroughs and Global Empowerment at V-Malaysia 2025

    July 11, 2025
    Over 8,000 global entrepreneurs gather …Read More »
  • Al-Hogail Thanks the Leadership for the Council of Ministers’ Approval of the Updated Regulation for Non-Saudis’ Ownership of Real Estate

    July 10, 2025
    RIYADH, Saudi Arabia, July 10, …Read More »
  • MicroCloud Hologram Inc. Proposes Multi-Qubit Quantum State Sharing Scheme: Sharing Multiple Quantum Information in One Operation

    July 10, 2025
    SHENZHEN, China, July 10, 2025 …Read More »
  • Hyundai Motor IONIQ 6 N Debuts at Goodwood Festival of Speed, Setting New Benchmark for High-Performance EVs

    July 10, 2025
    Hyundai Motor Company has unveiled …Read More »
  • Huawei Named a 2025 Gartner® Peer InsightsTM Customers’ Choice for File and Object Storage Platforms for the Fourth Year Running

    July 10, 2025
    SHENZHEN, China, July 10, 2025 …Read More »
  • Our Brands
  • CybersecAsia
  • MartechAsia
  • Home
  • About Us
  • Contact Us
  • Sitemap
  • Privacy & Cookies
  • Terms of Use
  • Advertising & Reprint Policy
  • Media Kit
  • Subscribe
  • Manage Subscriptions
  • Newsletter

Copyright © 2025 DigiconAsia All Rights Reserved.