The seed inference parameter for reproducibility

I thought the see parameter will give me reproducible ouput. But what I am seeing is that sometimes it add or removes some sentences when produces subsequent answers for the same question.


1 Like

Are you talking about DALLE API? AFAIK, there’s no seed in DALLE or any of the other models…

No, I am using gpt-4-turbo model.

1 Like

Ah, okay, it’s new, and I haven’t used it yet personally.

This thread might have some answers?

1 Like

I think they are referring to the API seed parameter launched with the new models, while a common seed will often produce the exact same responses, it is not 100% assured. It will be close but it may diverge from the point a minor change occurs.


1 Like

Here are some stats for using seed: prompt_engineering_experiments/experiments/DeterministicResultsOpenAI/Deterministic Results in OpenAI (report).ipynb at main · TonySimonovsky/prompt_engineering_experiments · GitHub