When training a machine learning model, a loss function is something you design that tells the model when its answers are right and when they're wrong. There are a bunch of different types, some catered to specific ML tasks like image classification (whether a plant has a bug on it or not) or regression (predicting a stock price), or predicting the next word in a sentence for an LLM.
As a model is trained, it predicts an answer to a question. If it's right, it gets a point. If it's wrong, it loses a point. After enough of these iterations, it starts to learn how to predict the correct answer.
There are lots of different types of loss functions, but behind the scenes, they're just telling your model "good job" or "try again." This is why it's so important, when training an ML or AI model, to have nicely curated, labeled data with a clear right and wrong answer.