Ask HN: Do you get worst answers from OpenAI API compared to ChatGPT?

https://news.ycombinator.com/item?id=39508347

by saga81 • 2 years ago

3 5 2 years ago

news.ycombinator.com

uma08• 2 years ago

yes, I've experienced this via their api. Although the GPT-4 model is a tad bit better in its responses compared to the turbo model

mikerg872• 2 years ago

Yes. Attempts to match api with the chat interface have proved futile. The api never seems to behave in the same way as the chat interface.

RockCoach• 2 years ago

Have you tried tweaking parameters like temperature, top_p, or seed value when sending the API request?

Beyond that and due to the probabilistic nature of the LLM response I'm not sure how a reproducible "matching" between chat interface and API could be achieved.

I'm working primarily with the API through my own wrapper and I noticed that I tend to give less detailed instructions than when I'm using the OpenAI chat interface often resulting in a less accurate response.

mikerg872• 2 years ago

Thanks. I will. I must confess, I have not tried the top_p or seed value. I guess my naive belief was that the the defaults in the api matched the OOTB experience of the web interface. shame on me

JojoFatsani• 2 years ago

It works pretty well for me. Is MacGPT. Maybe mess with your prompt.

Ask HN: Do you get worst answers from OpenAI API compared to ChatGPT?

Related Stories