Reverse engineering. Codex sometimes displays an advisory prompt when classifier trips - "Wait longer while we evaluate this request further or use a dumber model". If you do nothing, it'll just take some time and almost always succeed.
It does require some brainwashing of the model to get it to the state where model itself agrees to do RE work though. But at least it's all predictable.
It does require some brainwashing of the model to get it to the state where model itself agrees to do RE work though. But at least it's all predictable.