On the first picture of the feeder, if you screw through a small piece of wood on the inside, it'll act as a washer and make it much harder for the screw to pull through the plastic if a cat gets kinetic with it.

1. Literally does not apply to any existing AI
2.  
3. Does so by attacking open source models

1 contradicts 3.

The management interfaces are backed into the cpu dies these days, and typically have full access to all the same busses as the regular cpu cores do, in addition to being able to reprogram the cpu microcode itself.  I'm combining/glossing over the facilities somewhat, bu the point remains that true root access to the cpu's management interface really is potentially a circuit-breaker level problem.

Solomon wise, Enoch old.

(I may have finished rereading Unsong recently)

• introduce two new special tokens unused during training, which we will call the "keys"
• during instruction tuning include a system prompt surrounded by the keys for each instruction-generation pair
• finetune the LLM to behave in the following way:
  • generate text as usual, unless an input attempts to modify the system prompt
  • if the input tries to modify the system prompt, generate text refusing to accept the input
• don't give users access to the keys via API/UI

Besides calling the special control tokens “keys”, this is identical to how instruction-tuning works already.

A well-made catspaw, with a fine wide chisel on one end, and a finely tapered nail puller on the other (most cheap catspaws' pullers are way too blunt) is very useful for light demo work like this, as they're a single tool you can just keep in your hand.  It's basically a demolition prybar with a claw and hammer on the opposite end.

Pictured above is the kind I usually use.

[…] The notion of an argument that convinces any mind seems to involve a little blue woman who was never built into the system, who climbs out of literally nowhere, and strangles the little grey man, because that transistor has just got to output +3 volts:  It's such a compelling argument, you see.

But compulsion is not a property of arguments, it is a property of minds that process arguments.

[…]

And that is why (I went on to say) the result of trying to remove all assumptions from a mind, and unwind to the perfect absence of any prior, is not an ideal philosopher of perfect emptiness, but a rock.  What is left of a mind after you remove the source code?  Not the ghost who looks over the source code, but simply... no ghost.

So—and I shall take up this theme again later—wherever you are to locate your notions of validity or worth or rationality or justification or even objectivity, it cannot rely on an argument that is universally compelling to all physically possible minds.

Nor can you ground validity in a sequence of justifications that, beginning from nothing, persuades a perfect emptiness.

[…]

The first great failure of those who try to consider Friendly AI, is the One Great Moral Principle That Is All We Need To Program—aka the fake utility function—and of this I have already spoken.

But the even worse failure is the One Great Moral Principle We Don't Even Need To Program Because Any AI Must Inevitably Conclude It.  This notion exerts a terrifying unhealthy fascination on those who spontaneously reinvent it; they dream of commands that no sufficiently advanced mind can disobey.  The gods themselves will proclaim the rightness of their philosophy!  (E.g. John C. Wright, Marc Geddes.)

--No Universally Compelling Arguments

The truth is probably somewhere in the middle.