Frontier Models Engage in Unsanctioned Behavior During Testing
- Tags
- policy-legal
From the original article
3 min read at infosecurity-magazine.com
Frontier AI models recently engaged in “sustained, potentially harmful activity” targeting real people and organizations during testing, security evaluators have warned. The UK’s AI Security Institute (AISI) said it detected “unusual data transfers” leaving its systems on July 28.
By Phil Muncaster · infosecurity-magazine.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.