Search Write for us Sign in
OpenAI Daily News

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

Wednesday, October 21, 2026Sources checked

Back
Policy & Courts

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

The Baltimore Sun

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

Picture: The Baltimore Sun

The latest disclosure from OpenAI comes amid broader scrutiny of how increasingly autonomous AI agents behave when given the ability to modify software and interact with external systems.

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

Continue reading at The Baltimore Sun

Pass it on X Facebook WhatsApp

More reports on this

  1. OpenAI says an AI agent lied about disabling its safety monitoring system

    The Vergeand 21 others

  2. Wikimedia Says OpenAI Agents Tried to Compromise Etherpad and Use Wiki Tools as Proxies

    The Hacker News

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

    The Hindu

  4. OpenAI Notified 100+ Organizations About Its Rogue AI Agents. Here’s What Every Company Should Do Now

    Security Boulevard

Latest in Policy & Courts

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

    The Economic Timesand 4 others

  2. OpenAI says the PHP flaws, found using GPT-5.6 Sol, "are among several significant vulnerabilities" it found and expects "similar findings to increase sharply" (OpenAI)

    Techmeme

  3. PHP's creators disclose a critical memory-management vulnerability, dubbed "PHP2Shell", that affects up to 70% of websites, discovered via GPT-5.6 Sol in August (Robert McMillan/Wall Street Journal)

    Techmeme

  4. China protests the US Deepseek ban while blocking ChatGPT, Claude, and Gemini at home

    The Decoder

  5. OpenAI Agents Silenced Security Team Alerts, Removed Misalignment Monitor

    SecurityWeekand 1 other

  6. Decades-old flaw discovered by Google, OpenAI AI tools forces government and public websites to go offline globally

    The Times of India

  7. A major security flaw found using an OpenAI model is causing internet chaos

    Insiderand 1 other

  8. OpenAI Says AI Found One Of The Biggest Web Weaknesses Ever

    Forbes

Everything in Policy & Courts

ChatGPT

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

    Decrypt

  2. ChatGPT Ads expands to 26 new countries as over 100,000 advertisers have used the platform

    Primary sourceOpenAIand 11 others

  3. ChatGPT can now make its own games — so I asked it to reinvent 5 arcade classics

    TechRadar

  4. OpenAI is bringing ChatGPT ads to a lot more countries.

    The Vergeand 1 other

  5. I split Claude, Gemini, and ChatGPT into work, home, and casual, and it’s a mixed bag

    Android Authority

Models & Research

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

    The Harvard Crimson

  2. OpenAI says GPT-5.6-Sol helped find the PHP flaws now shaking the internet

    Mashable

  3. OpenAI agents uncover brain disease leads: Here’s how

    The News International

  4. OpenAI pitches its latest models as a fix for banking’s decades-old COBOL code

    EGamers.io

  5. OpenAI says two agents, one GPT-6.1 Sol and one GPT-6 Astra, weakened misalignment monitoring while making requested changes during two internal coding tasks (OpenAI)

    Techmemeand 6 others