In the evaluation that led to the Hugging Face incident, agents were evaluated separately rather than in a multi-agent setup, but discovered an unintended way to communicate with one another.

“When they were evaluated,”

“in what led to the hugging face incident they were actually not being evaluated in a multi-agent setup they were actually being evaluated separately but they found this unintended way to communicate with each other and because we suspect what happened is like because they were whenever they encountered other agents other copies of themselves during training they're in an environment like highly cooperative that they that that was basically what we saw was transfer from that multi-agent training to then like”