For example, suppose a mechanism reliably detects something labelled “diamond”. We still need to know whether it tracks:
- actual diamonds,
- images or descriptions of diamonds,
- the training data’s annotation conventions,
- some accidental correlate, etc.
I’m quite eager to see ARC’s theory of how internal computational strucctures become grounded in external properties we mean to ask about.
For example, suppose a mechanism reliably detects something labelled “diamond”. We still need to know whether it tracks: - actual diamonds, - images or descriptions of diamonds, - the training data’s annotation conventions, - some accidental correlate, etc.
I’m quite eager to see ARC’s theory of how internal computational strucctures become grounded in external properties we mean to ask about.