Whatever good thing the steering vector is doing for model behavior should be learnable as an effect generated by the model itself, so that it can be smart about it and integrate it with other good things it’s doing.
in reply to: 2051647989001707632
same thread: 2051647981485470197 2051647983758807115 2051647986120180225 2051647989001707632 2051698011240058939 2051699080644935778 2051699730493657369 2051790135918768437
cited on: observations
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.