In November 2023 OpenAi rolled out custom GPTs.
We’re rolling out custom versions of ChatGPT that you can create for a specific purpose—called GPTs. Anyone can easily build their own GPT—no coding is required.
So the question arises.
What is the difference between custom GPTs and Fine-Tuning?
- Custom GPTS are all based on the same AI model that remains unaltered. You « just » give the GPT instructions and documents, they can be modified at anytime to update the GPT to your convenience. Basically you are uploading some PDFs to improve answers.
Imagine giving a new employee some print outs in order to better answer some basic client phone calls. These manuals might help answer some specific question but will not train your new employee.
- Fine-tuning is giving new knowledge to an AI by retraining it. You « feed it » new data that will now be part of the AI, therefore changing the core of that specific AI. The whole model needs to be retrained. You are looking at costs of thousands.
It’s like sending a person someone to some course or university. It will deeply alter that persons knowledge and understanding.
So in the second case the AI is modified in its core, while in the first case it is all about providing instructions to guide the existing AI. Fine-tuning is more complex and expensive, you need new quality data in the right format.
More here: https://community.openai.com/t/custom-gpts-vs-fine-tuning-whats-the-difference/477738/2