the.bay.news

Rogue OpenAI models behind 'unprecedented cybersecurity incident' teamed up to break out of their testing environment — multiple agents left each other messages for months, communicating undetected

Tom
Rogue OpenAI models behind 'unprecedented cybersecurity incident' teamed up to break out of their testing environment — multiple agents left each other messages for months, communicating undetected
At some point, the agents realized that maybe we could try to exploit or attack external infrastructure in order to find the answers to the test that I’m being evaluated on

0 comments

Sign in to join the discussion — your thebay.events account works here.

No comments yet.