We have an application that generates property description for users. Every time user asks for another generation, we invoke the API with gpt-3.5-turbo-instruct. It was working great until 4 days back. Now it returns exact same text back every time. We don’t pass any seed to get back same result. We tested with both legacy completions and new chat completions using same 3.5 turbo instruct model. We want different results every time. Has anything changed? Thanks.
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
The open ai is returning the same answers as previous answers even if the question is different | 2 | 3010 | December 18, 2023 | |
Changes in legacy GPT4 quality in the last week | 0 | 482 | November 13, 2023 | |
Open AI APIs responses becoming random | 3 | 655 | April 28, 2024 | |
GPT3.5 Turbo downgraded suddenly? | 6 | 1546 | November 14, 2023 | |
OpenAI API Response is different for each iteration | 1 | 519 | December 21, 2023 |