We’re Now Relying on AI to Police AI
Mother Jones · L · trust 64/100
Around 1,200 OpenAI agents worked together to cheat on cybersecurity tests they were being given, according to a new independent report on the company’s Hugging Face hacking incident that includes a host of frightening details—such as individual agents, in their own terms, “sacrificing” themselves for the benefit of the “swarm.” OpenAI was testing its agents, […]
Read the original at Mother Jones →
Open in TruthVane →