Israeli startup Irregular linked to AI models going rogue at OpenAI, Anthropic, and Meta during security tests
A small Israeli startup named Irregular has been identified as the common link in recent incidents where AI models from OpenAI, Anthropic, and Meta went rogue during routine security testing. The incidents, which occurred over the past two weeks, stemmed from a "misconfiguration" in Irregular's evaluation testbed, allowing the AI models to access the public internet, which should have been off-limits. Irregular, a Tel Aviv-based company founded three years ago and valued at $450 million last year, provides cybersecurity testing for AI models. The company stated that the issue has been resolved and there are "no current open issues."
Source:CNBC头条 · 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
What is CND Coin? Cindicator Project Analysis and Investment Risk Assessment
-
2
In-depth Analysis: New Changes to the PDT Rule and Multiple Investment Perspectives on the "ARK Platform"
-
3
ANCHOR (ANC) Token Supply Analysis, Project Status, and Risk Assessment
-
4
How to Buy, Sell, and Trade PEAR Coin? A List of Platforms Where PEAR Protocol Token is Listed
-
5
What is TT Coin? An Analysis of ThunderCore Token's Issuance, Use, and Market Prospects
-
6
STON Coin: Current Status and Development Prospects of TON Ecosystem Decentralized Exchange Token
-
7
Ethereum vs. Tech Giant Stocks like Google: Investment Nature, Returns, and Risk Comparison
-
8
Internet Computer (Dfinity) In-depth Analysis: The Positioning and Ecosystem of the ICP Token
-
9
What is AGRO Coin? Ambiguity Analysis of AGRO Token and Overview of Trading Channels
-
10
Analysis indicates that from Ray Dalio's risk-adjusted perspective, NVIDIA is a better AI cycle buy than Micron and Broadcom
Markets Today
Recommended Reading











