For my current use case, Davinci seems more flexible, more reliable, and less likely to return the “As a large language model…” style responses. gpt-3.5-turbo is amazingly cheap and the latency is better, but after some experimentation, I’m coming to the realization that I may have to ship my new p…

For my product, I have realised that gpt turbo has been giving me better performance and accuracy both, so we have recently switched over to that for our testing phase. It is something that will vary product to product for sure.

Correct, seeing the same in my limited testing. Davinci is much stronger for general reasoning over large text for example.

I have noticed a big difference between chatGPT on the website and gpt-3.5-turbo. I ask it the same questions and get totally different responses. I have found that the responses on the website are much better than using the gpt-3.5-turbo API. I wonder if they really are the same thing?

I am actually getting great results - when I get the results… It seems that the API reacts with Bad Request when the “role” : “system” has “content” like this: “You are a writer tasked with creating engaging articles, blogs, and descriptions based on user prompts. Your goal is to use your creativit…

You haven’t said what is your use case - it would definitely help understanding what is going on and maybe give something back to the conversation.

[image] Securigy: I am actually getting great results - when I get the results… It seems that the API reacts with Bad Request when the “role” : “system” has “content” like this: That is not true if you write your code correctly, @Securigy I just took your system role content and tested it as…

Well, assuming that your statement is correct, and I do believe that it works on your side, then I don’t know then how to explain this - the same code is used in both cases - the short content of the “system” role works fine but the long produces Bad request. The same user content is used which is v…

After testing I’ve come to the conclusion that it’s apples to oranges. I hope that OpenAI establish the differences a little more. Although it’s literally in the name The current cGPT model is great for surface-level conversation, and continuing a conversation without prompt injection or topic dera…

Just curious what do you refer to by “iGPT (instruct)” - are those new API that I am not aware of? or existing ones that are in Instruct category?

I apologize. I figured that it’d be easier to call it Instruct. I’m referring to the already existent models such as Davinci

Davinci still seems like the gold standard, compared to turbo

API

ruby_coder March 6, 2023, 2:28am 23

If you set max_token:null this will overwrite the client max_token value the client sends to the API, but the OpenAI hard limit of 4096 tokens cannot be bypassed or overridden by any client method.

HTH

Topic		Replies	Views
Chat GPT4 1106 vs ChatGPT 4: Impressive drop in quality API gpt-4 , chatgpt	27	16005	February 14, 2024
Is it me or GPT4 consistently doesn't finish and cuts the answers? API	18	7121	April 11, 2024
Can I set max_tokens for chatgpt turbo? API	22	29846	March 14, 2023
Finetune model completion cut off too short Prompting	7	4093	January 17, 2023
JSON Mode with GPT-4 turbo stops after 1050 token Bugs api , gpt-4-turbo	26	5319	February 5, 2024

Davinci still seems like the gold standard, compared to turbo

Related topics