[jacinabox]

I just did a captcha the other day that asked the user to select which items can fit inside the sample item (which was a handbag). You'd think that a multimodal deep learning model could figure out what objects fit inside other objects if it's going to cure cancer or whatever, but no I'm assuming that it needs to be taught explicitly.

[Garlef]

There's a fun experiment with toddlers where they re-enter a room but the car they just sat in was replaced by a tiny version: They will try to get into the car even though only their foot fits in.

So size/scale is not as easy a concept to model in our minds as we might assume.

https://m.youtube.com/watch?v=OtngSHtz-cc

[Nextgrid]

This is a defense against AI, not a training step. Though a multimodal model should be able to pass it.