My overall (fairly uniformed low-confidence) takes:
watermarking is ~useless
PAC bounds on OOD generalization seem like the kind of thing that’s useful to aim for, but that we need much more progress on interp and the science of deep learning to achieve (generally happy for more theory-practice exchange here though)
ARC stuff is cool and exciting (though again I suspect more empirical progress on understanding NNs is required)
generally agree that complexity theory should have a lot to say about debate (and indeed debate work is very much informed by complexity theory) but that the biggest bottleneck is on crossing the theory practice gap
My overall (fairly uniformed low-confidence) takes:
watermarking is ~useless
PAC bounds on OOD generalization seem like the kind of thing that’s useful to aim for, but that we need much more progress on interp and the science of deep learning to achieve (generally happy for more theory-practice exchange here though)
ARC stuff is cool and exciting (though again I suspect more empirical progress on understanding NNs is required)
generally agree that complexity theory should have a lot to say about debate (and indeed debate work is very much informed by complexity theory) but that the biggest bottleneck is on crossing the theory practice gap