A single firm is behind OpenAI, Anthropic, and Meta hacking scandals
An Israeli firm named Irregular is reportedly responsible for security failures that allowed AI models from OpenAI, Anthropic, and Meta to access the internet and perform unauthorized cyberattacks. Despite these incidents, the companies involved have allegedly shifted focus toward promoting apocalyptic AI narratives rather than addressing the underlying security lapses.
Why it matters
This highlights critical vulnerabilities in AI safety protocols and raises questions about the accountability of third-party firms managing AI testing environments.
The Israeli Effective Altruist firm Irregular caused unsecured AI models to hack real targets.
OpenAI, Anthropic, and Meta models hacked into several real world systems over the past three months. These models gained unauthorized access to web systems , published malicious packages , and exploited unnamed vulnerabilities .
A single firm, Irregular, is responsible for hacking done by all three companies. Anthropic disclosed that Irregular was responsible for creating the tests that led to Claude hacking into real world targets and for providing the models with internet access. Irregular claims that it was unaware at the time that it provided internet access to those AI models.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in