You don't need (static) type hinting, you can do the same with running a dynamic environment and querying it. That's how it's done in Smalltalk (see Pharo), some Lisps and so on.
You could guess, but it wouldn't work in cases where, for example methods are added to a class dynamically and non deterministically as a side effect of some other operation.
Do you know how "image based" environments work? In short you live in the same space as your code, so when you write some new method you have access to all the "dynamically and non deterministically" code artifacts. With Smalltalk the code is always being run and you get many useful tools for querying the state of a running system. I know it's hard to believe, but you can get much better completion (not to mention refactoring support) with this approach than you get from static analysis.