Seems the advantage is that OP didn't need to write any code to extract information from the unstructured data (e.g. job title, company name, remote/not, salary, location, etc.). It seems you can feed GPT all of this data and ask it to return these fields.
Exactly. I am sure you can get similar results with some "traditional" NLP skills, but the good (bad?) thing is that they are not required when using one of the newer LLMs.