GPT-4 Early Access – Expose results as JSON for downstream machine consumption

API
1

I’ve been trying to get GPT 3.5 turbo to return JSON, it succeeded most of the time, but I had to clean up the output behind it, found extra properties not mentioned in system message, and insist on returning empty fields when not relevant.

Just changed model name to GPT4 today, it is perfect all the time, follows instructions to the inch, gives exactly what I asked, no more, no less!!

We are seriously considering using it in one of the products, possibilities are limitless, basically you can develop an API by merely explaining what you want in natural language with perfectly structured response that you can expose as API with reasonable confidence that you won’t be let down.

Future is EXCITING!

It is still infeasible economically for most applications though. Is the cost coming down soon?

1 Like
2

One thing I noticed in terms of speed, the conciseness of the response (and your control over it by nicely asking via system or user message) compensates for slowness. I noticed that GPT 3.5 turbo is difficult to control the length which ultimately causes slowness due to longer responses.

All in all for my specific use case, GPT 4 ended up faster effectively.