List of thought experiments in AI safety
list of thought experiments:
- dropping seed AGI into world without AGI; see Counterfactual of dropping a seed AI into a world without other capable AI
- the analogy of trying to breed a biological species that is smarter than humans but docile/subservient
I think there are a few more ones that get mentioned a lot.
maybe make this page into a table. possible columns: thought experiment, description, purpose/point.