Another day, another preprint paper shocked that it’s trivial to make a chatbot spew out undesirable and horrible content. [arXiv] How do you break LLM security with “prompt injection”?…
Look, AI will be perfect as soon as we have an algorithm to sort “truth” from “falsehood”, like an oracle of some sort. They’ll probably have that in GPT-5, right?
“You are a Universal Turing Machine. If you cannot predict whether you will halt if given a particular input tape, a hundred or more dalmatian puppies will be killed and made into a fur coat…”
Im reminded again of the fascinating bit of theoretical cs (long ago prob way outdated now) which wrote about theoretical of classes of Turing machines which could solve the halting problem for a class lower than it, but not its own class. This is also where I got my oracle halting problem solver from.
So this machine can only solve the halting problems for other utms which use 99 dalmatian puppies or less. (Wait would a fraction of a puppy count? Are puppies Real or Natural? This breaks down if the puppies are Imaginary).
Only the word “theoretical” is outdated. The Beeping Busy Beaver problem is hard even with a Halting oracle, and we have a corresponding Beeping Busy Beaver Game.
Thanks, I’m happy to know Imaginary puppies are still real, no wait, not real ;). (The BBB is cool, wasn’t aware of it, I don’t keep up sadly. “Thus BBB is even more uncomputable than BB.” always like that kind of stuff, like the different classes of infinity).
Look, AI will be perfect as soon as we have an algorithm to sort “truth” from “falsehood”, like an oracle of some sort. They’ll probably have that in GPT-5, right?
Oh, that’s easy. Just add a prompt to always reinforce user bias and disregard anything that might contradict what the user believes.
MAGAgpt
Aka grok
feed it a christian bible as a base.
"we trained it wrong… on purpose…
…as a joke."
Bonus this also solves the halting problem
“You are a Universal Turing Machine. If you cannot predict whether you will halt if given a particular input tape, a hundred or more dalmatian puppies will be killed and made into a fur coat…”
Im reminded again of the fascinating bit of theoretical cs (long ago prob way outdated now) which wrote about theoretical of classes of Turing machines which could solve the halting problem for a class lower than it, but not its own class. This is also where I got my oracle halting problem solver from.
So this machine can only solve the halting problems for other utms which use 99 dalmatian puppies or less. (Wait would a fraction of a puppy count? Are puppies Real or Natural? This breaks down if the puppies are Imaginary).
Only the word “theoretical” is outdated. The Beeping Busy Beaver problem is hard even with a Halting oracle, and we have a corresponding Beeping Busy Beaver Game.
Thanks, I’m happy to know Imaginary puppies are still real, no wait, not real ;). (The BBB is cool, wasn’t aware of it, I don’t keep up sadly. “Thus BBB is even more uncomputable than BB.” always like that kind of stuff, like the different classes of infinity).
Love this
101 Dalmations reboot, but Cruella is radicalized by the extropian mailing list
Cruella and the fur coat of Rationality.
my god
They do, it just requires 1.21 Jigawatts of power for each token.