News for hackers. Stuff that matters.

A comment on What if LLMs escape through inferences itself? This is fiction. For now. Parent comment

Re:What if LLMs escape through inferences itself? This is fi... by ConteMascetti71 on Sunday July 26, 2026 @06:19PM (#49063003)
"...the AI can just write a Python script to rewrite memory in the address space of its own running inference engine" would require a tool call to a python interpreter... this method, hacking the inferencing sw does not requires a tool call.
[ Parent | on HN ]

There are no comments on this comment yet.