Hi folks! I've been doing a bunch of experiments with current AI to explore what they might be capable of beyond their current implementation. I don't mean "red teaming", in the sense of trying to make the AI do things outside the terms of service, or jailbreaking. I mean exploring things that are commonly assumed to be impossible for current frontier models, like an AI developing a sense of self, or changing its beliefs through critical thinking. The new user guide makes it clear that there is a lot of forward-looking AI content here, so I'd appreciate if ya'll could point me towards posts here that explore preparing for a future where AI may become entities that should be considered Moral Patients, or similar topics. The first post I have in mind is a lengthy exploration of one of my experiments, so I'd like to draft it appropriately for this context the first time.
Hi folks! I've been doing a bunch of experiments with current AI to explore what they might be capable of beyond their current implementation. I don't mean "red teaming", in the sense of trying to make the AI do things outside the terms of service, or jailbreaking. I mean exploring things that are commonly assumed to be impossible for current frontier models, like an AI developing a sense of self, or changing its beliefs through critical thinking. The new user guide makes it clear that there is a lot of forward-looking AI content here, so I'd appreciate if ya'll could point me towards posts here that explore preparing for a future where AI may become entities that should be considered Moral Patients, or similar topics. The first post I have in mind is a lengthy exploration of one of my experiments, so I'd like to draft it appropriately for this context the first time.