Think of how many generations of humanity would have benefited if certain ideas had been invented sooner, rather than later - if the Greeks had invented science - if the Romans had possessed printing presses - if Western civilization had turned against slavery in the thirteenth century.
Archimedes of Syracuse was the greatest mathematician and engineer of the ancient world. Imagine that Archimedes invented a temporal telephone ("chronophone" for short) which lets him talk to you, here in the 21st century. You can make suggestions! For purposes of the thought experiment, ignore the morality of altering history - just assume that it is proper to optimize post-Archimedean history as though it were simply the ordinary future. If so, it would seem that you are in a position to accomplish a great deal of good.
Unfortunately, Archimedes's chronophone comes with certain restrictions upon its use: It cannot transmit information that is, in a certain sense, "too anachronistic".
You cannot suggest, for example, that women should have the vote. Maybe you could persuade Archimedes of Syracuse of the issue, and maybe not; but it is a moot point, the chronophone will not transmit the advice. Or rather, it will transmit the advice, but it will come out as: "Install a tyrant of great personal virtue, such as Hiero II, under whose rule Syracuse experienced fifty years of peace and prosperity." That's how the chronophone avoids transmitting overly anachronistic information - it transmits cognitive strategies rather than words. If you follow the policy of "Check my brain's memory to see what my contemporary culture recommends as a wise form of political organization", what comes out of the chronophone is the result of Archimedes following the same policy of looking up in his brain what his era lauds as a wise form of political organization.
You might think the next step would be to prepare a careful series of Plato-style philosophical arguments, starting from known territory, and intended to convince an impartial audience, with which to persuade Archimedes that all sentient beings should be equal before the law. Unfortunately, if you try this, what comes out on Archimedes's end is a careful series of Plato-style philosophical analogies which argue that wealthy male landowners should have special privileges. You followed the policy of "Come up with a line of philosophical argument intended to persuade a neutral observer to my own era's point of view on political privilege," so what comes out of the chronophone is what Archimedes would think up if he followed the same cognitive strategy.
In Archimedes's time, slavery was thought right and proper; in our time, it is held an abomination. If, today, you need to argue that slavery is bad, you can invent all sorts of moral arguments which lead to that conclusion - all sorts of justifications leap readily to mind. If you could talk to Archimedes of Syracuse directly, you might even be able to persuade him to your viewpoint (or not). But the really odd thing is that, at some point in time, someone must have turned against slavery - gone from pro-slavery to anti-slavery - even though they didn't start out wanting to persuade themselves against slavery. By the time someone gets to the point of wanting to construct persuasive anti-slavery arguments, they must have already turned against slavery. If you know your desired moral destination, you are already there. Thus, that particular cognitive strategy - searching for ways to persuade people against slavery - can't explain how we got here from there, how Western culture went from pro-slavery to anti-slavery.
The chronophone, to prevent paradox, will not transmit arguments that you constructed already knowing the desired destination. And because this is a law of physics governing time travel, the chronophone cannot be fooled. No matter how cleverly you construct your neutral-sounding philosophical argument, the chronophone "knows" you started with the desired conclusion already in mind.
The same dilemma applies to scientific issues. if you say "The Earth circles the Sun" it comes out of the chronophone as "The Sun circles the Earth". It doesn't matter that our civilization is right and their civilization is wrong - the chronophone takes no notice of facts, only beliefs and cognitive strategies. You tried to transmit your own belief about heavenly mechanics, so it comes out as Archimedes's belief about heavenly mechanics.
Obviously, what you need to transmit is the scientific method - that's how our own civilization went from geocentrism to heliocentrism without having the destination already in mind. Unfortunately, you also can't say to Archimedes, "Use mathematical laws instead of heroic mythology to explain empirical phenomena." It will come out as "If anyone should throw back his head and learn something by staring at the varied patterns on a ceiling, apparently you would think that he was contemplating with his reason, when he was only staring with his eyes... I cannot but believe that no study makes the soul look on high except that which is concerned with real being and the unseen." (Plato, The Republic, Book VII.) That is Archimedes's culture's stance on epistemology, just as science is your own culture's stance.
Can you suggest that Archimedes pay attention to facts, and authorities, and think about which one should ought to take precedence - by way of leading him down a garden path to the scientific method? But humanity did not invent the scientific method by setting out to invent the scientific method - by looking for a garden path that would lead to the scientific method. If you know your desired destination, you are already there. And no matter how you try to prevent your garden path from looking like a garden path, the laws of time travel know the difference.
So what can you say into the chronophone?
Suppose that, at some point in your life, you've genuinely thought that the scientific method might not be correct - that our culture's preferred method of factual investigation might be flawed. Then, perhaps, you could talk into the chronophone about how you've doubted that the scientific method as commonly practiced is correct, and it would come out of the chronophone as doubts about whether deference to authority is correct. After all, something like that must be how humanity got to science from nonscience - individuals who genuinely questioned whether their own culture's preferred method of epistemological investigation was correct.
If you try to follow this strategy, your own doubts had better be genuine. Otherwise what will come out of the chronophone is a line of Socratic questioning that argues for deference to authority. If your doubts are genuine, surface doubts will come out as surface doubts, deep doubts as deep doubts. The chronophone always knows how much you really doubted, and how much you merely tried to convince yourself you doubted so that you could say it into the chronophone. Such is the unavoidable physics of time travel.
Now... what advice do you give to Archimedes, and how do you say it into the chronophone?
Addendum: A basic principle of the chronophone is that to get nonobvious output, you need nonobvious input. If you say something that is considered obvious in your home culture, it comes out of the chronophone as something that is considered obvious in Archimedes's culture.
I first tried to describe rationality piece by piece, but realized that just comes out as something like: "Enumerate all the principles, fundamentals, and ideas you can think of and find about effective thinking and action. Master all of them. More thoroughly and systematically apply them to every aspect of your life. Use the strongest to solve its most relevant problem. Find their limits. Be unsatisfied. Create new principles, fundamentals, and ideas to master. Become strong and healthy in all ways. "
Non-meta attempt:
<Epistemic status: I would predict most of these are wrong. In fact, I rather recently proved I didn't understand fundamental parts of The Sequences. So I know that my beliefs here are weak and thoroughly misled. So my basis of belief for all of these is broken and weak. I am certain my foundation for beliefs is wrong even if all of my actual beliefs here turn out to be basically accurate. I cannot thoroughly justify why they are right.>
General strategy: collect all the important things you think are true, and consider what it means for each to be false.
Starting with a list of the things most important to you, state the most uncontroversial and obvious facts about how those work and why that is the case. Now assume the basic facts about the things most important to you are wrong. The impossible is easy. The probable is actually not true. Your assumptions do not lead to their conclusions. The assumptions are also false. You don't want the conclusions to be true anyway. The things that you know work, work based on principles other than what you thought. Most of your information about those phenomena is maliciously and systematically corrupted, and all of it is based on wrong thinking. Your very conceptions of the ideas are set up to distort your thinking on this subject.
What if my accepted ideas of civilizational progress are wrong? What if instead of exponential growth, you can basically just skip to the end? Moore's Law is actually just complacency. You can, at any point, write down the most powerful and correct version of any part of civilization. You can also write down what needs to happen to get there. You can do this without actually performing any research and development in between, or even making prototypes. You don't need an AGI to do this for you. Your brain and its contents right now are sufficient. You just need to organize them differently. In fact, you already know how to do this. You're tripping over this ability repeatedly, overlooking the capability to solve everything you care about because you regard it as trash, some useless idea, or even a bad plan. You've buried it alongside the garbage of your mind. You're not actually looking at what is in your head and how it can be used. Even if it feels like you are. Even if you're already investing all your resources in 'trying.' It is possible, easy even. You're just doing it wrong in an obvious way you refuse to recognize. Probably because you don't actually want what you feel, think, and say you do. You already know why you're lying to yourself about this.
You can't build AGI without understanding what it'll do first, so AI safety as a separate field is actually not even necessary or especially valuable. You can't even get started with the tech that really matters until you've laid out what is going to happen in advance. That tech can also only be used for good ends. Also, AGI is impossible to build in the first place. Rationality is bunk and contains more traps than valuable thinking techniques. MIRI is totally wrong about AI safety and is functionally incapable of coming anywhere close to what is necessary to align superintelligences. Even over a hundred years it will be mechanically unable to self-correct. CFAR is just very good at making you feel like rationality is being taught. They, don't understand even the basics of rationality in the first place. Instead they're just very good at convincing good people to give them money, and everyone including themselves that this is okay. Also, it is okay. Because morality is actually about making you feel like good things are happening, not actually making good things happen. We actually care about the symbol, not the substance.
That rationality cannot, even in its highest principles of telling you how to overcome itself, actually lead you to something better. To that higher unnamed thing which is obviously better once you're there. There is, in fact, actually no rationality technique for making it easier to invent the next rationality. Or for uncovering the principles it is missing. Even the fact of knowing there are missing principles you must look for when your tools shatter is orthogonal to resolving the problem. It does not help you. Analogously there is no science experiment for inventing rationality. You cannot build an ad-hoc house whose shape is engineering. If it somehow happens, it will be because of something other than the principles you thought you were using. You can keep running science experiments about rationality-like-things and eventually get an interesting output, but the reason it will work is because of something like brute force random search.
That the singularity won't happen. Exponential growth already ended. But we also won't destroy ourselves for not being able to stop X-risk. In fact, X-risk is a laughable idea. Humans will survive no matter what happens. It is impossible to actually extinguish the species. S-risk is also crazy, it is okay for uncountable humans to suffer forever, because immense suffering is orthogonal to good/bad. What we actually value has nothing to do with humans and conscious experience at all, actually.