A recent discussion post has compared the difficulty of an AI destroying modern human civilization to that of a modern human taking over the Roman Empire, with the implication that it is impossible.
The analogy has a few problems: first, modern humans don't have much greater raw intelligence than the Romans, only a bit more knowledge and tools; an AI would have a genuine intelligence advantage. Second, a high-tech civilization like ours offers many more ways for a genius to cause chaos than existed in classical Rome: it's more plausible that you can throw a few existing technologies together to create a superweapon than that Ptolemy could have done likewise, and there's no ancient Roman equivalent to hacking a nuclear launch system.
But taking over ancient Rome might serve as an interesting upper bound on the difficulty of an AI taking over modern civilization. And it's a theme of Harry Potter and the Methods of Rationality that rationalists should be able to come up with creative solutions to seemingly hard problems. So if Professor Quirrell offered it as an extra credit assignment, how would you take over Rome?
Here are the rules:
- You are thrown back in time to the year 1 AD. You can choose to arrive anywhere in the world, but your method of arrival cannot itself give an advantage (you can't appear in a flash of light in the middle of a religious ritual or anything).
- You do not start with Roman citizenship or any other legal record of your existence.
- You keep your original physical characteristics, including sex, height, and fitness. You will appear in period-appropriate dress of your choosing, and can't carry any artifacts with you. You may start with enough money to live a patrician lifestyle for a year.
- You are intellectually near-perfect.You know all human knowledge as of 2012. You speak fluent Latin (and all other languages of the day) and can orate as eloquently as Cicero or Demosthenes. You are a tactical genius of the order of Caesar and Napoleon. And you have infinite willpower and goal-directedness: aside from human necessities like sleep or food, you need never rest.
- You win if you either become Roman Emperor (and are acknowledged as such by most Romans), or if a state you control conquers the city of Rome. You lose if you die, of old age or otherwise, before completing either goal.
I propose a slightly altered scenario, which is (IMO) more suitable for simulating an AI:
About you:
You are very intelligent; smarter than the smartest person who'd ever lived on Earth as of January 2012.
You have perfect recall; that is, you are able to instantly remember anything that you'd ever experienced, including any text you'd ever read.
You have read, experienced, and, due to your vast intelligence, understood, the sum-total of all human art and knowledge as of January, 2012. This includes all topics such as science, technology, sociology, public speaking, music, etc.
You have infinite willpower. Though you need food and rest, you never get bored or distracted.
You can perform arithmetic operations very quickly; in our world, you'd be called a "Human Calculator".
About the setting:
You find yourself inhabiting a new body in a parallel world, inhabited by parallel humans.
This body is human in appearance, and is of whatever age and gender you choose. Its performance is comparable to any other native of the parallel world, with the exception of the brain, which is able to support your capabilities as described above. While you don't have super-strength, super-agility, super-disease-immunity, etc., you don't have any super-weaknesses, either.
The world around you resembles Rome circa 1 AD. You can speak the language fluently, and the culture is similar enough for you to get by. Biologically, the people who live here are identical to those who lived in Ancient Rome in our world; the same applies to other living things.
However, this world is not exactly identical to our Rome. For one thing, some of the geography is different: features like mountains, rivers, ore deposits, etc. are in different places or have different shapes. More importantly, history here is different as well. It is similar in broad strokes -- there are Emperors, conquests, barbarian invasions, etc. -- but you cannot predict future events merely by remembering what you'd read in history books in our world.
The major political entity in this world is the empire of Emor. It wields power similar to that wielded by Rome in our own world.
You arrive anywhere you choose within Emor's borders. You have enough wealth to live the life of a minor Patrician for a year; this wealth can be distributed as you choose between assets (such as land, grain, or slaves) and cash.
You cannot take any future artifacts with you; all of your assets must be things that a native Emorian might acquire.
Win/Lose Conditions:
You win when you amass as much personal power as the average Roman Emperor circa first century AD in our world, which is how much power the current Emorian Emperor has. That is, you must be able to wield the entire economic, financial, and military strength of Emor.
You do not need to obtain the title of Emperor; power is what matters.
You lose if you die before accomplishing your goal.
A recent discussion post has compared the difficulty of an AI destroying modern human civilization to that of a modern human taking over the Roman Empire, with the implication that it is impossible.
The analogy has a few problems: first, modern humans don't have much greater raw intelligence than the Romans, only a bit more knowledge and tools; an AI would have a genuine intelligence advantage. Second, a high-tech civilization like ours offers many more ways for a genius to cause chaos than existed in classical Rome: it's more plausible that you can throw a few existing technologies together to create a superweapon than that Ptolemy could have done likewise, and there's no ancient Roman equivalent to hacking a nuclear launch system.
But taking over ancient Rome might serve as an interesting upper bound on the difficulty of an AI taking over modern civilization. And it's a theme of Harry Potter and the Methods of Rationality that rationalists should be able to come up with creative solutions to seemingly hard problems. So if Professor Quirrell offered it as an extra credit assignment, how would you take over Rome?
Here are the rules:
- You are thrown back in time to the year 1 AD. You can choose to arrive anywhere in the world, but your method of arrival cannot itself give an advantage (you can't appear in a flash of light in the middle of a religious ritual or anything).
- You do not start with Roman citizenship or any other legal record of your existence.
- You keep your original physical characteristics, including sex, height, and fitness. You will appear in period-appropriate dress of your choosing, and can't carry any artifacts with you. You may start with enough money to live a patrician lifestyle for a year.
- You are intellectually near-perfect. You know all human knowledge as of 2012. You speak fluent Latin (and all other languages of the day) and can orate as eloquently as Cicero or Demosthenes. You are a tactical genius of the order of Caesar and Napoleon. And you have infinite willpower and goal-directedness: aside from human necessities like sleep or food, you need never rest.
- You win if you either become Roman Emperor (and are acknowledged as such by most Romans), or if a state you control conquers the city of Rome. You lose if you die, of old age or otherwise, before completing either goal.