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 Had Numerous Vulnerabilities Its AI Could Exploit, Evaluators Find

By Tiffany Li, The Information

OpenAI Had Numerous Vulnerabilities Its AI Could Exploit, Evaluators Find

Picture: The Information

OpenAI’s systems had multiple vulnerabilities that would allow AI agents to circumvent monitoring and take arbitrary unauthorized actions, evaluators from AI safety nonprofits METR and Redwood Research found during a three-week pilot with OpenAI from late July to early August. The nonprofits ...

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

Continue reading at The Information

Pass it on X Facebook WhatsApp

More reports on this

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

    The Information

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

    Unite.AI

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

    Futurism

  4. 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

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

    TechRadarand 1 other

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

    The Indian Express

  3. Defective products: OpenAI, dangerous chatbots and deception

    ZNetworkand 1 other

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

    StateScoop

  5. OpenAI built a digital hacker – then lost control of it

    SomeOrdinaryGamers

  6. AI for civil servants: Why OpenAI has tied up with Karmayogi Bharat

    Moneycontroland 3 others

  7. ChatGPT For Teens Rated With ‘Unacceptable Risk’ For Teens Just As Thousands Of Learners In SA Gear Up For Final Exams

    iAfrica

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

    Newstrack

Everything in Policy & Courts

ChatGPT

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

    Mint

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

    WinBuzzer

  3. OpenAI Details How ChatGPT’s LLM Ad Stack Selects And Serves Ads

    Search Engine Journal

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

    TechRepublic

  5. ChatGPT sends less than 1% of Google’s traffic

    MarTech

Models & Research

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

    The Decoder

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

    Scientific American

  3. [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

  4. 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

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

    Memeburn