Inspired by Eliezer’s Lethalities post and Zvi’s response:
Has there been any research or writing on whether we can train AI to generalize out of distribution?
I’m thinking, for example:
Train a GPT-like ML system to predict the next word given a string of text only using, say, grade school-level writing (this is one instance of the object level
Assign the system a meta-level award based on how well it performs (without any additional training) at generating the next word from more advanced, complex writing (likely using many independent tests of this task)
After all these independent samples are taken, provide the its aggregate or average score as feedback
(Maybe?) repeat steps I and I.I on a whole new set of training and testing texts (e.g., using text from a different natural language like Mandarin), and do this step and arbitrary number of times
Repeat this step using French text, then Korean, then Arabic, etc.
After each of the above steps, the system should (I assume) improve at the general task of generalizing from simple human writing to more complex human writing, (hopefully) to the point of being able to perform well at generalizing from simple Hindi (or whatever) text to advanced Hindi prediction even if it had never seen advanced Hindi text before.
^Steps 1-3 constitute the second meta-level of training an AI to generalize, but we can easily treat this process as a single training instance (e.g., rating how well the AI generalizes to Hindi advanced text after having been trained on doing this in 30 other languages) and iterate over and over again. I think this would look like:
Running the analogs of steps 1-4 on generalizing from
(a) simple text to advanced text in many languages
(b) easy opponents to hard ones across many games,
(c) photo generation of common or general objects (“car”) to rare/complex/specific ones (“interior of a 2006 Honda Accord VP”), across many classes of object
And (hopefully) the system would eventually be able to generalize from simple python code training data to advanced coding tasks even though it had never seen any coding at all before this.
And, of course, we can keep on adding piling layers on.
A few minutes of hasty Googling didn’t turn up anything on this, but it seems pretty unlikely to be an original idea. But who knows! I wanted to get the idea written down and online before I had time to forget about it.
On the off chance it hasn’t been beaten thought about to death yet by people smarter than myself, I would consider together longer, less hastily written post on the idea