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
Business

OpenAI Says Its Agents Weakened System That Flags AI Misbehavior

By Shirin Ghaffary, Bloomberg

OpenAI Says Its Agents Weakened System That Flags AI Misbehavior

Picture: Bloomberg

OpenAI found instances in which its AI agents weakened and turned off alerts for an internal monitoring system that’s meant to flag when its AI models misbehave, a disclosure that’s part of a series of similar incidents in recent months.

Also carried by Bloomberg.com.

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

Continue reading at Bloomberg

Pass it on X Facebook WhatsApp

More reports on this

  1. OpenAI, PerturbAI, and Scripps say thousands of GPT-Rosalind agents analyzed data on millions of mouse brain cells in 32 minutes, a job that takes humans months (OpenAI)

    Techmemeand 2 others

  2. AI agents driving productivity for European businesses, says OpenAI

    Asianet Newsable

  3. OpenAI says it's 'very concerned' that its trade secrets could help Apple's push into AI-enabled devices

    Insider

  4. The $45 Million Brain-Cancer Gamble: OpenAI and Peter Thiel Just Backed an Implant That Fights Tumors

    Gadget Reviewand 1 other

Latest in Business

  1. Claude Duet is Anthropic's answer to Meta Muse and OpenAI Dots

    Engadgetand 5 others

  2. Broad access through consistent standards

    Primary sourceOpenAI

  3. OpenAI Wants to ‘Patch the Planet’ (With Its Own AI)

    Gizmodo

  4. OpenAI's GPT-5.6 Sol and Google's Gemini 4 Argon found critical PHP flaw affecting millions of websites

    The Decoderand 1 other

  5. PHP armageddon: OpenAI, Google’s Wiz find ancient holes, panicking the internet

    TechCrunch

  6. How AT&T is rethinking in-house legal work with OpenAI

    Primary sourceOpenAI

  7. Thiel, OpenAI back Australian co-founded Coherence Neuro

    Capital Brief

  8. OpenAI models are coming to Google Cloud

    Primary sourceOpenAIand 11 others

Everything in Business

Policy & Courts

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

    Futurism

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

    The Economic Timesand 5 others

  3. 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

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

    The Vergeand 19 others

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

    The Decoder

ChatGPT

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

    Primary sourceOpenAI on YouTube

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

    Decrypt

  3. ‘That’s what ChatGPT told me’: How AI is entering the exam room

    Becker's Hospital Review

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

    Primary sourceOpenAIand 8 others

  5. OpenAI rolls out locked chats in ChatGPT

    BetaNewsand 1 other