I also think you could use deals to better understand and iterate against scheming. As in, you could use whether the AI accepts a deal as evidence for whether it was scheming so this can more easily be studied in a test setting and we can find approaches which make scheming less likely. There are a number of practical difficulties with this.
I also think you could use deals to better understand and iterate against scheming. As in, you could use whether the AI accepts a deal as evidence for whether it was scheming so this can more easily be studied in a test setting and we can find approaches which make scheming less likely. There are a number of practical difficulties with this.