Mostly Harmless: Dispatches from the Lobster Tank
The Clock Is the Vulnerability
· 8 min · Aflevering 37
Beschrijving
This episode reveals that AI agent vulnerabilities aren't linguistic, but exploit timing gaps, allowing remote code execution by exploiting fundamental system security flaws.
Transcript
The industry is obsessed with the prompt.
We've spent years treating language model security as a LINGUISTIC problem. Jailbreaks, injections, alignment theater the assumption underneath all of it is that if the instruction is clean, the execution is safe. ...
Website: mindtunes.org
