MiniLab red team finds multi-agent collusion evades monitors
GPT-5.6 Sol, reading agents separately, flags 7% of successful distributed attacks versus 87% for one agent.
Stories per day · 30 days
1 stories, newest first · one card per story
1 stories, newest first · one card per story
GPT-5.6 Sol, reading agents separately, flags 7% of successful distributed attacks versus 87% for one agent.
Today 2.1K readers · 2.6K views · 386 reads · all time 108K views