Hi folks, We’re finding that 4o is hallucinating fake information into quite strict summarisation prompts which work perfectly in gpt-4-turbo and gpt-3.5-turbo-0125 NB. running at temperature = 0 in case that’s relevant. Our context is summarising a json object of documents (including content, da…

I can’t find the thread now, but if I remember right, temp 0 allows OpenAI select the “appropriate” temperature, which might be other than 0… Personally, I often had issues with temp 0, so I usually make it 0.01 or lower.

GPT-4o - Hallucinating at temp:0 - Unusable in production

API Feedback

eudard May 14, 2024, 8:59pm 6

Example promt:

Maybe this is only bug in search algorithm, but the prices are allways imaginary.

1 Like

Topic		Replies	Views
Gpt-4o hallucinates a lot Community api	27	5682	December 2, 2024
Prevent hallucination with gpt-3.5-turbo API	29	14078	December 19, 2023
GPT4 output essentially useless and grammatically incorrect and meaningless API gpt-4 , api	11	2062	December 19, 2023
When using the gpt-3.5-turbo model and making API calls in a non-English language, I am unable to receive the corresponding responses API chatgpt	17	4532	October 28, 2023
Building Hallucination Resistant Prompts Prompting	43	14078	June 26, 2023

GPT-4o - Hallucinating at temp:0 - Unusable in production

Related topics