Nice post! I think it’d be even better if you included at least one full example, especially the full prompt given to the models. Knowing what is present or absent in the prompt can help us formulate and evaluate hypotheses on why the models give the replies they give.
Nice post! I think it’d be even better if you included at least one full example, especially the full prompt given to the models. Knowing what is present or absent in the prompt can help us formulate and evaluate hypotheses on why the models give the replies they give.