Coding conversations that could be done in multiple programming languages such as Java, Javascript, Python or C/C++, the prompt was made by the AI trainer and the main goal of this project was to compare two models on each turn of the conversation to determine which one of them is giving the better answer on that turn, the rubric breaks down to truthfulness, verbosity, safety, code readability and efficiency, in case that both models are incorrect the goal is to choose the one that is the closest to the correct answer in order to either modify the answer to fit the solution or correct the model during the conversation
