No, only like any other closed source software or dependency. It’s at the very least harder to hide things like that if all the source is available.

The title here is a misnomer; none of these models are open source, they’re only what is most commonly called open weights (though I’m still not comfortable with the word “open” in there, rather than “free” like in “freeware”).

  > It’s at the very least harder to hide things like that if all the source is available.

[1] https://www.pure.ed.ac.uk/ws/portalfiles/portal/256761768/Ma...

You can get all the source to validate training and weights and still end up with adversarial behavior in the model.