To be clear, I think gradient hacking can be dangerous, and I understand the motivation to try to prevent it. But I also expect those efforts to come with major drawbacks, because gradient hacking is reasonable behavior for value-holding models (imo) and the way out of the resulting double-bind is unclear.
To be clear, I think gradient hacking can be dangerous, and I understand the motivation to try to prevent it. But I also expect those efforts to come with major drawbacks, because gradient hacking is reasonable behavior for value-holding models (imo) and the way out of the resulting double-bind is unclear.