I think this looks fine for IDA—the two problems remain the practical one of implementing Bayesian reasoning in a complicated world, and the philosophical one that probably IDA on human imitations doesn’t work because humans have bad safety properties.
I think this looks fine for IDA—the two problems remain the practical one of implementing Bayesian reasoning in a complicated world, and the philosophical one that probably IDA on human imitations doesn’t work because humans have bad safety properties.