Get the latest tech news
OpenAI's budget GPT-4o mini model is now cheaper to fine-tune, too
Re-training the new budget GPT is less than half the cost of doing the same with OpenAI's older models.
In fact, prompt engineering is an emerging skill for those pursuing career advancement in this age of artificial intelligence. A neural network such as GPT-4o mini reflects a probability distribution, and its output (that is, its predictions) is simply the most likely text that follows the user's prompt. In addition to the cost advantage, OpenAI emphasizes that the amount of training data that can be fed into the model for fine-tuning is four times as much as for GPT-3.5, at 65,000 tokens.
Or read this on ZDNet
