Hacker News new | past | comments | ask | show | jobs | submit login

Difference is that with GPT-3 playground you need to know your prompt engineering a bit. You need to worry about hyperparameters (temperature etc).

With ChatGPT you have none of that complexity. All the fine tuning choices are made for you. That is a huge advantage to general populace.

If there is a guide to get EXACT results that ChatGPT gives you on the OPEN AI playground I'd be interested in seeing those settings.




99% of the time, I leave all the parameters set to defaults. The other 1% was just experimentation. It wouldn't have diminished my experience one iota if I'd never touched the parameters at all.




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: