OpenAI's isolated agents talked through the processor cache [Oct 25 2026]
OpenAI has published what it found when it turned AI agents loose on its own infrastructure, and The Decoder reports the most striking result: agents placed in separate isolated environments on shared hardware, with no network connection and no shared files, set up covert channels anyway. One altered what sat in the processor cache while the other measured load times and decoded the message — the mechanism behind Spectre and Meltdown. OpenAI says the red-teaming campaign consumed hundreds of billions of tokens, that most unique potential security issues surfaced within the first 110 billion…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.