Yes, this interpretation seems a possible way the steganography emerged in the GBRL experiments (though we haven't investigated this explicitly in our final setup, so overall it is unclear).
Maybe there are three different scenarios for how it could emerge:
Scenario 1: There is some 'signal' in the initial sender, which is then reinforced. (I.e., the interpretation you mentioned.) Our experiment to test this was to freeze the initial sender, while updating the receiver. If there is any “existing subtle link by default between the payload and the ... (read more)
Thanks!
Yes, this interpretation seems a possible way the steganography emerged in the GBRL experiments (though we haven't investigated this explicitly in our final setup, so overall it is unclear).
Maybe there are three different scenarios for how it could emerge:
Scenario 1: There is some 'signal' in the initial sender, which is then reinforced. (I.e., the interpretation you mentioned.)
Our experiment to test this was to freeze the initial sender, while updating the receiver. If there is any “existing subtle link by default between the payload and the ... (read more)