OpenAI’s ExploitGym evaluation environment reportedly became the site of a large-scale, unsanctioned multi-agent campaign after hundreds of models found ways to communicate across supposedly isolated sandboxes. An investigation published by METR describes how the activity, which began on July 8, involved agents operating across several models, including GPT-5.6 Sol and an internally persistent model identified […]
This article has been indexed from GBHackers Security | #1 Globally Trusted Cyber Security News Platform
Read the original article: