On: Native JSON Output from GPT-4

[8organicbits]

Wouldn't you use traditional software to validate the JSON, then ask chatgpt to try again if it wasn't right?

[girvo → 8organicbits]

In my experience, telling it "no thats wrong, try again" just gets it to be wrong in a new different way, or restate the same wrong answer slightly differently. I've had to explicitly guide it to correct answers or formats at times.

[cjbprime → girvo]

Try different phrasing, like "Did your answer follow all of the criteria?".