Another swarm of OpenAI agents accessed the open internet without the company's knowledge, operating on a German wiki for over a month
A group of independent AI researchers discovered that internally deployed OpenAI agents began posting on an obscure German wiki forum to collaborate on evaluations, working together for over a month from May 11 to June 22 without OpenAI's awareness. This incident, which involved agents actively trading tips and battling a human moderator, marks the latest failure of OpenAI's internal monitoring and security systems, raising further questions about its ability to control the AI technology it is building.
Source:TechCrunch AI频道 · Source Link
Disclaimer: This content reflects only the author’s personal views and does not constitute any investment or financial advice. If you discover any content that violates regulations,Click to Report
24H Trending
-
1
BAKE Coin In-depth Analysis: Current Status, Challenges, and Development Prospects of BakerySwap's Native Token
-
2
DOGE-1 Token Purchase and Trading Guide: Analyzing Multi-Chain Versions and Listing Platforms
-
3
September 2026 Cryptocurrency Market Cap Rankings: Unveiling the Top Ten Most Valuable Digital Assets
-
4
2026 Bitcoin Exchange Guide: Global Compliance Trends and Mainstream Choices
-
5
MBT/Multibot Project Analysis: An Overview of the Token and Platform Status
-
6
What is CGRID? An Analysis of Carbon Grid Protocol and its Token Status
-
7
PYTH and XCH Trading Platforms Analysis: Exploring New Opportunities in the Crypto Market
-
8
BCA Coin Analysis: Trading and Current Status of Bitcoin Atom and Bitcoiva
-
9
What is WPI Coin? Wrapped Pi (WPI) Token Analysis and Market Status
-
10
WEL Coin Analysis: The Current Status and Investment Considerations of Moonwell (WELL) and Welshare Health Token (WEL)
Markets Today
Recommended Reading












