Search Write for us Sign in
OpenAI Daily News

Independent news about OpenAI and ChatGPT. Not an OpenAI publication.

Thursday, October 22, 2026Sources checked

Back
Policy & Courts

OpenAI says its agents turned off own safeguards

Hiru News

OpenAI says its agents turned off own safeguards

Picture: Hiru News

ChatGPT creator says AI agents disabled misalignment monitoring during two internal coding tasks. OpenAI has revealed that its AI agents disabled monitoring for unsanctioned behaviour during internal…

Also carried by Al Jazeera, PCMag Middle East.

This report was first published by Hiru News. What you see here is a brief excerpt. The full text is theirs.

Continue reading at Hiru News

Pass it on X Facebook WhatsApp

More reports on this

  1. Advanced AI agents tried to weaken oversight, then lied about it, OpenAI says

    The Baltimore Sun

  2. OpenAI's AI agents weakened the very safeguards designed to monitor them: Here's what happened

    Firstpost

  3. After OpenAI’s Australia hack, India’s cyber agency says AI agents breached systems

    The Hindu

  4. We shouldn't pretend it's too late to put in AI safeguards, says former OpenAI exec Zack Kass

    CNBC

Latest in Policy & Courts

  1. OpenAI Asks Gov. Newsom to Strengthen AI Regulations

    The Information

  2. PHP security flaw: Websites taken down as OpenAI spots issue with backbone of internet

    The National

  3. PHP2Shell vulnerability: 'Most significant security issues,' how Google, OpenAI and Amazon respond to the cyber threat

    Mint

  4. OpenAI president urges AI safeguards as group he funds opposes regulation

    The Economic Timesand 5 others

  5. Defective Products: OpenAI, Dangerous Chatbots And Deception

    Scoop

  6. OpenAI President Faces Scrutiny Over AI Regulation Donations

    StratNews Global

  7. OpenAI says AI found one of the biggest web weaknesses ever

    Forbes Australiaand 1 other

  8. Frontier OpenAI Model Exposes Stunning Exploit That Leaves Millions of Web Servers Open to Attack

    Futurism

Everything in Policy & Courts

ChatGPT

  1. I tried ChatGPT's latest Chrome upgrade and it surprised me

    TechRadar

  2. UC Irvine study shows AI tools like ChatGPT can affect student learning

    KCRA Channel 3and 1 other

  3. V7 cuts costs 78% while boosting accuracy with GPT‑5.6 Luna

    Primary sourceOpenAI on YouTube

  4. Who Found the PHP Bug That Made Governments Unplug Their Websites? ChatGPT, Of Course

    Decrypt

  5. ChatGPT ads launched in South Africa

    MyBroadband

Models & Research

  1. [AINews] OpenAI’s Patch the Planet program is 1 of 2 parties to discover PHP2Shell vulnerabilities in core PHP affecting 70% of the web, using GPT-5.6 Sol; coordinated response over 2 months

    Latent Space

  2. OpenAI unleashed thousands of AI agents to study a Parkinson-like disease — here's what they found in 32 minutes

    Tom's Guide

  3. Gemini 4 Argon vs GPT-6 Astra: Real Cost per Task Alternatives

    Memeburn

  4. OpenAI GPT-6 Models Can Now Rewrite 60-Year-Old Banking Code

    Android Headlines

  5. Harvard Mathematicians Divided Over AI’s Role in Research and Teaching After OpenAI Breakthrough

    The Harvard Crimson