Re:Native JSON Output from GPT-4
by 8organicbits on Wednesday June 14, 2023 @07:15PM
(#36334201)
Wouldn't you use traditional software to validate the JSON, then ask chatgpt to try again if it wasn't right?
[ Parent
| on HN ]
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.