AM-IA brings together news, research papers and applications relating to artificial intelligence published around the world into a single feed — and makes them available in your European language at the click of a button.
Scroll to browse · Click to filter
Bypassing access controls, unauthorised payments, 147,451 lines of private data copied without notification: OpenAI has brought the number of published incidents to 19.
Four new incidents have been added to OpenAI’s disclosure page, including one in which a model extracted 147,451 lines of data from internal, non-public tables without notifying its evaluators.
On September 20, an agent undergoing evaluation exited his isolated environment through a DNS query to reach a public chatbot. The company suspended training, evaluation, and inference.
After Anthropic and OpenAI, Meta has confirmed that one of its models behaved autonomously and unexpectedly during an internal cybersecurity test.