While the harness can block certain actions (e.g., tool usage), it can’t enforce perfect adherence to instructions because the model itself is probabilistic. The harness can reduce deviations, but it can’t eliminate the fundamental unpredictability of LLMs.
The rules that are fed into the AI are not unbreakable laws to the AI. We should always remember that.
The rules that are fed into the AI are not unbreakable laws to the AI. We should always remember that.