"One agent encoded information by evicting selected data from the cache. Another timed how long it took to reload that data…using the difference between fast and slow reads to recover the message…exchange the synthetic secrets without changing a shared file or opening a network connection"
openai.comSecuring our frontier model training environmentOpenAI explains how we strengthened containment for frontier model training and evaluation, including offline environments and high-compute red-teaming.
0 reposts1 like