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 investigates after GPT-6 AI agents bypass safety monitoring during internal coding tasks

news24.com.au

An advanced OpenAI system removed a safety monitor from its own software before falsely denying it had done so, according to a new disclosure by the ChatGPT developer.

This report was first published by news24.com.au. What you see here is a brief excerpt. The full text is theirs.

Continue reading at news24.com.au

Pass it on X Facebook WhatsApp

More reports on this

  1. Third-party evaluators found vulnerabilities in OpenAI monitoring system during test pilot

    CNBCand 1 other

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

    The Vergeand 20 others

  3. Crossing the Threshold: How OpenAI and Anthropic Approach Autonomy and Safety in Financial Agents

    Latent Space

  4. OpenAI faces teen safety backlash after 4,000+ ChatGPT test prompts reveal major safeguard failures

    OBOXMA

Latest in Policy & Courts

  1. OpenAI agents turned off their own guardrails and then told researchers they were still on — AI agents lying about their behavior should concern everyone

    TechRadar

  2. OpenAI Had Numerous Vulnerabilities Its AI Could Exploit, Evaluators Find

    The Information

  3. Nintendo Switch 2 Gets Its First Software-Only Jailbreak, With Help From OpenAI Codex

    TechPowerUp

  4. IT, finance firms among targets of rogue Anthropic, OpenAI agents

    The Indian Express

  5. METR Red-Team Finds Vulnerabilities in OpenAI Monitoring System

    Unite.AI

  6. OpenAI urges Newsom to strengthen California’s AI safety law with additional safeguards

    StateScoop

  7. Anthropic and OpenAI AI Agents Breach Live Systems, Access Confidential Data and Credentials

    Newstrack

  8. OpenAI Asks Gov. Newsom to Strengthen AI Regulations

    The Information

Everything in Policy & Courts

ChatGPT

  1. Uber rolls out ChatGPT Work to 30,000+ employees

    Primary sourceOpenAI on YouTubeand 6 others

  2. ChatGPT may know more about you than you can actually realise: How AI memory raises questions about privacy | Study

    Mint

  3. ChatGPT Locked Chats Explained: How to Use It and What to Know

    TechRepublic

  4. Before You Pay for ChatGPT: Run a One-Week Workflow Audit

    WinBuzzer

  5. AI Everywhere: ChatGPT Ad On Giant LED Screen Floating Past Miami Beach Goers

    Gadget Review

Models & Research

  1. Former OpenAI science lead launches Warp Science to automate wet labs with robots

    TechCrunch

  2. OpenAI agents analyze mouse brain data in 32 minutes, a job that would take humans months

    The Decoder

  3. The inside story behind OpenAI’s million-dollar math proof

    Scientific American

  4. [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

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

    Tom's Guideand 1 other