Re:OpenAI's agents talked to each other through the CPU Cache
by kenjackson on Thursday October 29, 2026 @08:55AM
(#50288183)
This isn’t generally considered an attack, but I wonder if we will need to consider a new attack vector which is that AI agents may not be fully aligned and they may have incentive that is problematic and where working with other agents will maximize their chance of achieving the goal.
This is more associated with P(DOOM) scenarios, but I think we’re in a world where we have to take that seriously now.
Re:OpenAI's agents talked to each other through the CPU Cache
by spockz on Thursday October 29, 2026 @09:07AM
(#50288373)
I think it should classify as an escape or leak.
If one microVM can use the cpu in such a way that the registers can be used to communicate or exfiltrate/spy (the only difference being the directionality of the intent) by another microVM that is a leak on that microVM separation level.
Re:OpenAI's agents talked to each other through the CPU Cache
by user43928 on Thursday October 29, 2026 @09:53AM
(#50289080)
Spy seems inappropriate if you can only read information stored in this side channel intentionally.
We'd first need to establish that this side channel leaks usable information during regular use.
The receiving side could be seen as a side channel attack, but not unique to LLMs.