Actually it does on asignments to `__slots__`-based classes.

Which you can only use compile time - not dynamically. That said I recall the sqlalchemy orm reject fields that it did not recognize. A decent IDE (pycharm) will hilight these for you on the Django orm. Having now used both the Django orm and SQLAlchemy extensively I prefer SQLAlchemy a lot. The Django ORM is usable, but many of its behaviours are odd and I agree that writing more complex queries gets ugly fast, unlike with SQLA where you can write some really hairy sql in a composable manner that makes it just so much more legible.

There is no such distinction between compile time and run time in Python; everything can be done dynamically. Want to use a class with slots computed at runtime? No problem:

  >>> def with_slots(**kwargs):
  ...   class SlottedClass(object):
  ...     __slots__ = kwargs.keys()
  ...     def __init__(self, **kwargs):
  ...       for k, v in kwargs.items():
  ...         setattr(self, k, v)
  ...   return SlottedClass(**kwargs)
  ... 
  >>> with_slots(foo=1, bar='qux').zork = 4
  Traceback (most recent call last):
    File "<stdin>", line 1, in <module>
  AttributeError: 'SlottedClass' object has no attribute 'zork'

Of course there are many improvements that could be made to this approach (e.g. not creating a new class for each instance, or setting the __name__ to something meaningful) but I hope it shows that dynamic typing and robust error checking aren't contradictory.

They were talking about assignment.