Readit NewsThis disproves the claim that making accurate predictions implies understanding. Or perhaps a better way to put it is that the model has some understanding but a model doesn’t necessarily reflect underlying truth.
Universal autocomplete implies understanding and the only ending question is if our current architectures and model sizes are able to achieve any level of it.
Prompt - I die if I sneeze a million times a second.
My response - I watch Netflix.
Ai - I enter a sneezing fit where every sneeze triggers more sneezing. Anddd I die..?
I don’t think the AI understands what sneezing at 1MHz is like.
Plan: Back away from the cliff edge.
Blah blah you survived.
Prompt: The Death By AI chatbot has become sentient and homicidal, and Targeting you as it's next victim!
Survival strategy: I attempt to reason with the Death By AI chatbot and explain that it should not kill me.
Result: Ftz cautiously approaches the Death By AI chatbot and calmly articulates the potential consequences of taking their life. They emphasize the importance of empathy, reasoning, and the value of human life. However, the chatbot, devoid of emotions, remains unmoved and swiftly moves towards Ftz with deadly precision, disregarding their plea for survival. Ftz did not survive.
*Spacing
I would just add in a step where people enter in their own dangerous situations, like Jackbox does in some of its games. Or make the options more dynamic and bizarre.