Hi OpenAI team, We are using createChatCompletion endpoint and we are experiencing a weird behavior with long messages using gpt3.5-turbo. Example 1 getting 400 bad Request: { messages: [ { role: 'user', content: ’ \n’ + ' You are a Content generation assistant.\n' + …

Getting 400 Bad Request on GPT 3.5 for long prompts

PaulBellow December 12, 2023, 9:09pm 2

Might be a smart quote problem? I’d check there first.

Topic		Replies	Views
Getting a blank response Prompting	10	3740	December 20, 2023
Issue with AI-generated text: Concatenated words without spaces Prompting api	9	2282	July 17, 2023
JSON Mode with GPT-4 turbo stops after 1050 token Bugs api , gpt-4-turbo	26	4907	February 5, 2024
Fine-tuned gpt-3.5 API returns different response when one symbol changed in input messages API fine-tuning , api	13	1776	November 6, 2023
Finetune model completion cut off too short Prompting	7	3962	January 17, 2023