Unwanted injection into new GPT-4o model system messages by OpenAI

Not a new policy, just our general philosophy.

Unfortunately we have no plans to allow pre-fill. I wish we could release pre-fill as it’s super nice for prompt engineering. From our POV the problem is that it’s so effective, it gets around some of our policy/safety training. So in this case the lack of control is not because we want to oversimplify the dev experience, but because we don’t want to screw up on policy/safety.

3 Likes